release: v3.36.0 — 3 AI roles + ContextOps + comprehension debt

Added: - guide/roles/ai-roles.md: §14 MLOps Engineer, §15 AI Developer Advocate, §16 AI Orchestration Engineer with full profiles (responsibilities, skills, entry paths, salary benchmarks, career matrix rows) - 4 resource evaluations (Packmind ContextOps, comprehension debt, Addy Osmani agents.md anti-pattern, Claude Swarm Monitor) Changed: - guide/roles/ai-roles.md: ToC renumbered, Career Decision Matrix +3 rows, Salary Benchmarks +3 rows, removed "Orchestration Engineer" from What's Not a Role - docs/for-cto.md, for-cio-ceo.md, for-tech-leads.md: updated docs positioning - guide/ecosystem: mcp-servers-ecosystem.md + third-party-tools.md updates - guide/roles/learning-with-ai.md: content updates Bump: 3.35.0 → 3.36.0 (VERSION, README, cheatsheet, ultimate-guide, reference.yaml, llms.txt, llms-full.txt, machine-readable/llms.txt) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-17 09:14:26 +01:00 · 2026-03-17 09:14:26 +01:00 · 19bdc910cc
commit 19bdc910cc
parent c2a642dabe
19 changed files with 669 additions and 48 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@ -6,6 +6,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).

 ## [Unreleased]

+## [3.36.0] - 2026-03-17
+
 ### Documentation

 - **Resource Evaluation #076**: Addy Osmani — "Stop Using /init for AGENTS.md" (Feb 23, 2026). Score 3/5. Secondary synthesis of ETH Zürich paper (already evaluated). Verified: ETH Zürich claims confirmed. Unverified: Lulla et al. (ICSE JAWs 2026) and ACE framework (ICLR 2026) — no findable academic source. Arize AI concept verified, specific numbers uncorroborated. Integration: added discoverability filter + anchoring risk concepts to §3.1, added research note (ETH Zürich), added `/init` warning in commands table.
--- a/README.md
+++ b/README.md
@ -6,7 +6,7 @@

 <p align="center">
  <a href="https://github.com/FlorianBruniaux/claude-code-ultimate-guide/stargazers"><img src="https://img.shields.io/github/stars/FlorianBruniaux/claude-code-ultimate-guide?style=for-the-badge" alt="Stars"/></a>
-  <a href="./CHANGELOG.md"><img src="https://img.shields.io/badge/Updated-Mar_13,_2026_·_v3.35.0-brightgreen?style=for-the-badge" alt="Last Update"/></a>
+  <a href="./CHANGELOG.md"><img src="https://img.shields.io/badge/Updated-Mar_17,_2026_·_v3.36.0-brightgreen?style=for-the-badge" alt="Last Update"/></a>
  <a href="./quiz/"><img src="https://img.shields.io/badge/Quiz-271_questions-orange?style=for-the-badge" alt="Quiz"/></a>
  <a href="./examples/"><img src="https://img.shields.io/badge/Templates-204-green?style=for-the-badge" alt="Templates"/></a>
  <a href="./guide/security/security-hardening.md"><img src="https://img.shields.io/badge/🛡️_Threat_DB-15_vulnerabilities_·_655_malicious_skills-red?style=for-the-badge" alt="Threat Database"/></a>
@ -872,7 +872,7 @@ See [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines.

 ---

-*Version 3.35.0 | Updated daily · Mar 13, 2026 | Crafted with Claude*
+*Version 3.36.0 | Updated daily · Mar 17, 2026 | Crafted with Claude*

 <!-- SEO Keywords -->
 <!-- claude code, claude code tutorial, anthropic cli, ai coding assistant, claude code mcp,
--- a/2
+++ b/2
@ -1 +1 @@
-3.35.0
+3.36.0
--- a/docs/for-cio-ceo.md
+++ b/docs/for-cio-ceo.md
@ -48,7 +48,7 @@ This is not a chatbot. It's a production tool.

 **License**: $100/month per developer (Claude Max). For a team of 10, that's $1,000/month — less than 2 days of external consulting.

-**Training**: one structured day is enough for a team of 10 to 15 people. A free Brown Bag Lunch (1h) lets you test team interest before committing to anything.
+**Training**: one structured day is enough for a team of 10 to 15 people. A free Brown Bag Lunch (1h) lets you test team interest before committing to anything — and costs you nothing, I do those for the networking and the challenge.

 **Doing nothing**: your developers use unvetted free tools, with no data policy, no audit trail. That scenario carries more risk than structured adoption.

@ -70,11 +70,11 @@ This is not a chatbot. It's a production tool.

 **Option 1 — You want to understand before deciding**: ask your CTO for a 30-minute demo on a real use case from your codebase.

-**Option 2 — You want to move fast**: a free Brown Bag Lunch (1h, in-person or remote) covers the fundamentals for your executive and technical teams simultaneously.
+**Option 2 — You want to move fast**: a free Brown Bag Lunch (1h, in-person or remote) covers the fundamentals for your executive and technical teams simultaneously. Free — I do these for the networking and the challenge.

 **Option 3 — You already have teams using it**: a configuration audit (half-day) identifies active risks and optimization opportunities.

-→ [Contact Florian Bruniaux](https://florianbruniaux.github.io/claude-code-ultimate-guide-landing/) — availability and pricing
+→ [Contact Florian Bruniaux](https://florian.bruniaux.com/) — availability and, depending on the mission, potentially pricing

 ---

--- a/docs/for-cto.md
+++ b/docs/for-cto.md
@ -91,11 +91,12 @@ The real cost isn't the subscription — it's unstructured adoption creating sec

 If you want to accelerate adoption or get an independent assessment of your current setup:

-**Brown Bag Lunch (1h, free)** — executive + team intro, live demo, Q&A
-**Config audit (half-day)** — review your current setup against security and productivity standards
-**Team formation (1-3 days)** — hands-on training, your codebase, your workflows, measurable outcomes
+**Brown Bag Lunch, talk, or panel (1-3h, free)** — executive + team intro, live demo, Q&A, or speaker slot. I do these for the pleasure of it — getting challenged, sharing what I know, building network. No strings attached.

-→ [Contact Florian Bruniaux](https://florianbruniaux.github.io/claude-code-ultimate-guide-landing/) for availability and pricing
+**Config audit (half-day)** — review your current setup against security and productivity standards.
+**Team formation (1-3 days)** — hands-on training, your codebase, your workflows, measurable outcomes. Not something I'm actively seeking right now, but I'm open to the right conversation.
+
+→ [Contact Florian Bruniaux](https://florian.bruniaux.com/) for availability and, depending on the mission, pricing

 ---

--- a/docs/for-tech-leads.md
+++ b/docs/for-tech-leads.md
@ -81,11 +81,11 @@ Full coverage in WP03 — Security and WP06 — Privacy *(whitepapers, coming so

 If you want structured onboarding rather than self-learning:

- **Brown Bag Lunch (1h, free)** — intro session covering core concepts + team config live
- **Team formation (1-2 days)** — hands-on, your codebase, your workflows
- **Config audit** — review your current setup against security and productivity best practices
+- **Brown Bag Lunch, talk, or panel (1-3h, free)** — intro session, live demo, or speaker slot. Done for the pleasure of it: sharing, getting challenged, building network.
+- **Config audit** — review your current setup against security and productivity best practices.
+- **Team formation (1-2 days)** — hands-on, your codebase, your workflows. Not something I'm actively looking for, but open to the right conversation.

-→ [Contact Florian Bruniaux](https://florianbruniaux.github.io/claude-code-ultimate-guide-landing/) for availability
+→ [Contact Florian Bruniaux](https://florian.bruniaux.com/) for availability and, depending on the mission, potentially pricing

 ---

--- a/docs/resource-evaluations/076-addy-osmani-agents-md-init-antipattern.md
+++ b/docs/resource-evaluations/076-addy-osmani-agents-md-init-antipattern.md
@ -0,0 +1,195 @@
+# Evaluation: Addy Osmani — Stop Using /init for AGENTS.md
+
+**Resource Type**: Blog Article (Research Synthesis + Practitioner Guidance)
+**Author**: Addy Osmani (Director, Google Cloud AI)
+**Date**: February 23, 2026
+**Source**: LinkedIn post + full article (https://lnkd.in/gkmZ3HJs)
+**Evaluation Date**: 2026-03-17
+**Evaluator**: Claude Sonnet 4.6
+
+---
+
+## 1. Content Summary
+
+Research-backed critique of the `/init` auto-generation workflow for AGENTS.md / CLAUDE.md context files, synthesizing two 2026 academic papers with practitioner architecture recommendations.
+
+**Key claims**:
+- **ETH Zurich study**: LLM-generated context files reduce task success by 2-3% and inflate costs by 20%+, because agents can already discover what those files contain
+- **Lulla et al. (ICSE JAWs 2026)**: Human-authored context files reduced wall-clock runtime by 28.64% and token consumption by 16.58% — but only because they contained genuinely non-discoverable information
+- **The discoverability filter**: the only criterion for adding a line is whether the agent can find it by reading the code; if yes, delete it
+- **"Pink elephant" anchoring effect**: mentioning a technology in CLAUDE.md biases the agent toward it every session, even if it's deprecated or rarely used
+- **Static monolithic files are architecturally flawed**: they load the same context regardless of task type, wasting tokens on irrelevant instructions
+- **ACE framework (ICLR 2026)**: dynamic routing layer outperformed static CLAUDE.md approaches by 12.3% on agent benchmarks
+- **Arize AI automated optimization**: iterative prompt learning yielded +5.19% accuracy cross-repo, +10.87% in-repo
+- **Mental model shift**: CLAUDE.md as diagnostic tool for codebase friction, not permanent configuration
+
+**Depth**: ~3,500 words, research synthesis + practical architecture recommendations. Source credibility is high — Osmani is Google Cloud AI Director, article cites peer-reviewed 2026 papers.
+
+---
+
+## 2. Initial Scoring: 4/5 (High Value)
+
+| Score | Meaning | Action |
+|-------|---------|--------|
+| 5 | Critical — fills major gap | < 24h |
+| **4** | **High value — significant improvement** | **< 1 week** |
+| 3 | Moderate — useful complement | When time available |
+| 2 | Marginal — skip or minimal mention | — |
+| 1 | Out of scope — reject | — |
+
+### Justification
+
+**What the guide already covers (§3.1, line 4532)**:
+- CLAUDE.md hierarchy (global / project / local)
+- Minimum Viable CLAUDE.md concept
+- "Auto-generated CLAUDE.md files tend to be generic, bloated" — line 4589
+- Anti-pattern: preemptively documenting everything
+- What Claude auto-detects (tech stack, directory structure, conventions)
+
+**What's missing from the guide — filled by this article**:
+- **Research backing**: The guide has correct intuitions but zero empirical evidence. Osmani provides two 2026 papers with concrete numbers.
+- **The `/init` anti-pattern explicitly named**: line 21308 lists `/init` as a command without any caveat. The article makes the cost explicit: +20% cost, -2-3% success.
+- **Discoverability filter as decision rule**: "Can the agent find this by reading the code?" is nowhere in the guide as an explicit framework.
+- **Anchoring/pink elephant concept**: context contamination from stale or irrelevant tech mentions — not covered anywhere in the guide.
+- **Dynamic context routing architecture**: 3-layer model (protocol file + skill files + maintenance subagent) — aligns with the guide's skills system but the connection is never made.
+- **Scale implications**: 15-20% cost overhead compounds across CI/CD runs — no coverage in the guide's cost sections.
+
+**Why 4/5 and not 5/5**:
+- The guide already gives the right advice; this strengthens it with data and adds missing concepts
+- A 5/5 would require the guide to be actively wrong or have a complete gap — here it's partially covered but under-evidenced
+- Some claims (ACE framework +12.3%, Arize +5.19%) are from research with limited real-world validation
+
+---
+
+## 3. Comparative Analysis
+
+| Aspect | This Resource | Guide §3.1 |
+|--------|--------------|------------|
+| Minimum CLAUDE.md principle | ✅ Research-backed | ✅ Present (intuition only) |
+| `/init` anti-pattern | ✅ Named, quantified | ❌ Listed as command, no caveat |
+| Discoverability filter | ✅ Explicit decision rule | ❌ Implied but not stated |
+| Anchoring / pink elephant effect | ✅ Named concept with mechanism | ❌ Not covered |
+| Dynamic context routing | ✅ 3-layer architecture | ❌ Not covered |
+| Research citations (2026 papers) | ✅ ETH Zurich, Lulla et al. | ❌ None |
+| Scale/cost at CI/CD volume | ✅ Quantified overhead | ❌ Not covered |
+| CLAUDE.md as diagnostic tool | ✅ Central mental model | Partially (anti-pattern section) |
+| Hierarchy of CLAUDE.md files | ✅ Mentioned | ✅ Well covered |
+| Automated optimization loop | ✅ Arize AI approach | ❌ Not covered |
+
+---
+
+## 4. Integration Recommendations
+
+### Where to integrate
+
+**Primary: §3.1 Memory Files (CLAUDE.md) — line ~4589**
+
+Add a dedicated subsection "The Discoverability Filter" immediately after the existing "Minimum Viable CLAUDE.md" section:
+
+```markdown
+### The Discoverability Filter
+
+Before adding any line to CLAUDE.md, apply this test: **can the agent discover
+this by reading the codebase?** If yes, don't add it.
+
+Two 2026 research studies quantify the cost of ignoring this: LLM-generated
+context files (the output of `/init`) reduce task success by 2-3% and inflate
+costs by 20%+ because they duplicate what agents find by exploring the repo
+anyway (ETH Zurich, 2026). Human-authored files that contain genuinely
+non-discoverable information perform better: -28.64% wall-clock time,
+-16.58% token consumption (Lulla et al., ICSE JAWs 2026).
+
+What earns a line:
+- Tooling preference that can't be inferred: `Use uv, not pip`
+- Operational landmine: `legacy/ is deprecated but imported by prod — do not delete`
+- Non-obvious convention: `auth module uses custom middleware — do not refactor to Express standard`
+
+What does not earn a line:
+- Directory structure (agent reads it in the first tool call)
+- Tech stack (agent reads package.json / go.mod / Cargo.toml)
+- Testing conventions (agent reads existing tests)
+```
+
+**Secondary: `/init` command documentation — line ~21308**
+
+Add a warning note alongside the command listing that auto-generated output tends to be redundant and can hurt performance.
+
+**Tertiary: New "Context Anchoring" warning in §3.1**
+
+Add a callout about the pink elephant / anchoring effect: mentioning a technology in CLAUDE.md biases the agent toward it every session. Stale entries are worse than no entries.
+
+**Optional: Advanced patterns section**
+
+The 3-layer dynamic routing architecture (protocol file + persona/skill files + maintenance subagent) could slot into §4 (agents) or §9 (advanced workflows) as an architecture pattern for teams running agents at scale.
+
+### Priority
+
+**High** — the `/init` usage is common, the anti-pattern is quantified, and the guide already gives the right advice without the evidence to back it. Adding the data strengthens the guide's credibility.
+
+---
+
+## 5. Challenge Results (technical-writer agent)
+
+The challenger **downgraded the score to 3/5** with substantive reasoning.
+
+**Core finding**: This is a secondary synthesis article, not a primary source. The guide already evaluated the ETH Zurich paper directly (`agents-md-empirical-study-2602-11988.md`, scored 4/5). Osmani's article derives most of its authority from that same paper — scoring the derivative higher than the source is backwards.
+
+**Unverified claims the evaluation initially missed**:
+- **Lulla et al. (ICSE JAWs 2026)**: -28.64% / -16.58% numbers are suspiciously precise for a 2026 paper with no arXiv link or DOI provided
+- **ACE framework (ICLR 2026)**: +12.3% claim — ICLR 2026 results not fully public as of March 2026
+- **Arize AI +5.19% / +10.87%**: commercial observability company, incentive to publish favorable benchmarks, source unclear
+- **"Pink elephant" anchoring**: Osmani's interpretive layer, not a finding from any cited study
+
+**Conflict of interest flag**: Osmani is Director at Google Cloud AI, which competes with Anthropic in the AI coding tools space. His framing of Claude Code's `/init` as an anti-pattern is not neutral commentary. The underlying research remains valid, but the framing context should be noted.
+
+**What Osmani genuinely adds** (not covered by ETH Zurich eval):
+- The dynamic routing layer argument (static monolithic AGENTS.md as architecturally flawed) — if ACE framework checks out, this is a forward-looking direction worth tracking
+- Practitioner authority signal: widely-read voice from Google reaching this conclusion documents where community consensus is moving
+
+**Integration recommendation revised**:
+- Do not create a new section
+- Fold Osmani's practitioner framing into the already-planned ETH Zurich callout as a convergence note (2 sentences)
+- Verify Lulla et al. and ACE framework before any integration of those claims
+- Flag Arize AI numbers as unverified commercial claims
+
+---
+
+## 6. Fact-Check (Perplexity + existing evaluations)
+
+| Claim | Status | Source |
+|-------|--------|--------|
+| ETH Zurich: LLM-generated files -2-3% task success, +20% cost | ✅ | Verified — matches `agents-md-empirical-study-2602-11988.md` (arXiv 2602.11988, peer-reviewed) |
+| ETH Zurich: developer-written files +4% success | ✅ | Same source — confirmed |
+| 100% of auto-gen files contained codebase overviews | ✅ | Consistent with ETH Zurich paper findings |
+| `uv`: 1.6 uses/task when mentioned vs <0.01 without | ⚠️ | Plausible ETH Zurich finding, specific numbers not independently verified |
+| **Lulla et al. (ICSE JAWs 2026)**: -28.64% wall-clock, -16.58% tokens, 124 PRs | ❌ | **NOT FOUND** — no arXiv, no DOI, no academic search hit via Perplexity. Specific precision of these numbers is a red flag. Paper may not exist or may not be publicly available yet. |
+| **ACE framework (ICLR 2026)**: +12.3% vs static approach | ❌ | **NOT FOUND** — no paper matching "Agentic Context Engineering" from ICLR 2026 found in academic search. |
+| **Arize AI**: +5.19% cross-repo, +10.87% in-repo accuracy | ⚠️ | **Partially verified** — Arize blog post exists (arize.com/blog/optimizing-coding-agent-rules..., Oct 2025, updated Mar 2026) and confirms automated optimization yields "10-15% improvement." The specific split numbers (+5.19% / +10.87%) do not appear in Perplexity results — may be Osmani's own restatement of the blog data. |
+| Addy Osmani role as Director, Google Cloud AI | ✅ | LinkedIn profile |
+| Article date: February 23, 2026 | ✅ | Article header |
+
+**Summary of verification**:
+- **Verified**: ETH Zurich claims (backed by peer-reviewed arXiv paper already in our eval database)
+- **Unverifiable**: Lulla et al. and ACE framework — no findable published source; treat as unverified
+- **Partially verified**: Arize AI — concept confirmed, specific numbers uncorroborated
+
+**Corrections to previous evaluation**: The initial evaluation incorrectly marked Lulla et al. and ACE framework as verified. These are unverified claims from a secondary synthesis article. Osmani may be citing pre-publication papers, conference proceedings not yet indexed, or may have imprecise numbers in the synthesis.
+
+---
+
+## 7. Final Decision
+
+**Score**: 3/5 (Moderate — derivative synthesis with unverified secondary claims)
+
+**Action**: Partial integration — ETH Zurich-backed points only, fold into existing planned callout
+
+**Confidence**: High on ETH Zurich claims, Low on Lulla/ACE/Arize specific numbers
+
+**What to integrate** (ETH Zurich-verified only):
+1. Add `/init` anti-pattern warning to the command listing (~line 21308): "Auto-generated output from `/init` falls into the LLM-generated category — ETH Zurich research shows these reduce task success by ~3% and add 20%+ cost. Review and prune before committing."
+2. Osmani's "discoverability filter" framing ("can the agent find this by reading the code?") is a useful pedagogical tool — cite as practitioner convergence with the ETH Zurich finding
+3. The anchoring/pink elephant concept is editorial but valid — add as a callout in §3.1 without claiming it's a study finding
+
+**Do not integrate**: Lulla et al. numbers (-28.64% / -16.58%), ACE framework +12.3%, Arize specific numbers (+5.19% / +10.87%) — all unverifiable.
+
+**Pre-condition**: Ship the ETH Zurich integration (`agents-md-empirical-study-2602-11988.md`, 4/5) first. This article rides on that work.
--- a/docs/resource-evaluations/076-packmind-contextops-platform.md
+++ b/docs/resource-evaluations/076-packmind-contextops-platform.md
@ -0,0 +1,110 @@
+# Resource Evaluation #076 — Packmind: ContextOps Platform for AI Coding Agents
+
+**Source:** [GitHub — PackmindHub/packmind](https://github.com/PackmindHub/packmind) / [Demo use cases](https://github.com/PackmindHub/demo-use-case-skills)
+**Type:** Open-source platform + SaaS layer — engineering standards distribution for AI coding agents
+**Evaluated:** 2026-03-17
+
+---
+
+## 📄 Content Summary
+
+Packmind is a "ContextOps" platform (Packmind's own term) that captures engineering standards once and distributes them as AI-readable context across all AI coding agents a team uses.
+
+1. **Standards Distribution** — Single source of truth for coding rules, architecture patterns, naming conventions. Generates `CLAUDE.md` + slash commands + skills for Claude Code, `.cursor/rules/*.mdc` for Cursor, `.github/copilot-instructions.md` for Copilot, `AGENTS.md` for generic agents.
+2. **MCP Server** — Lets Claude Code (or any MCP-capable agent) create and manage playbook standards interactively during a session.
+3. **Continuous Learning Loop** — Claimed workflow: bug fixed → root cause + resolution captured via Skill+MCP → playbook update proposed → human validates → distributed across repos. (Claimed behavior, no reproducible benchmark found.)
+4. **Knowledge Ingestion from Team Tools** — Demo repo shows 6 ready-made use cases pulling context from GitHub PR comments, Slack, Jira, GitLab MRs, Confluence, Notion via their MCP servers.
+5. **Self-hostable** — Docker/Kubernetes, Apache-2.0 CLI. SaaS layer at packmind.com with unspecified pricing.
+
+**Traction:** 245 GitHub stars, 22 CLI releases in 6 months (v0.19.0→v0.22.0), active commits as of March 16 2026, 29 open issues.
+
+---
+
+## 🎯 Relevance Score
+
+| Score | Meaning |
+|-------|---------|
+| 5 | Essential — Major gap in the guide |
+| 4 | Very relevant — Significant improvement |
+| 3 | Relevant — Useful complement |
+| 2 | Marginal — Secondary info |
+| 1 | Out of scope — Not relevant |
+
+**Score: 4/5**
+
+The guide covers CLAUDE.md authorship per-project but has zero coverage of organizational-scale standards distribution across repos and teams. Packmind addresses exactly that gap. It also introduces the only tool with measurable traction specifically targeting multi-agent context sync (Claude Code + Copilot + Cursor + Windsurf from a single source).
+
+---
+
+## ⚖️ Comparison
+
+| Aspect | Packmind | Our Guide |
+|--------|----------|-----------|
+| CLAUDE.md per-project authorship | ✅ Automated via CLI | ✅ Well documented |
+| Org-scale standards distribution | ✅ Core feature | ❌ Missing — real gap |
+| Multi-agent sync (Copilot, Cursor, Windsurf) | ✅ Native support | ⚠️ Partial (third-party-tools) |
+| MCP server for context management | ✅ Ships one | ✅ Documented (mcp-servers-ecosystem) |
+| `.claude/rules/` modular pattern at org scale | ✅ Packmind = org-level version | ✅ Project-level documented |
+| Continuous learning loop from failures | ✅ Claimed (unverified) | ❌ Missing |
+| Security implications of centralized context | ⚠️ Not documented by them | ✅ Security section exists |
+
+---
+
+## 📍 Integration Recommendations
+
+**Priority High — `guide/ecosystem/third-party-tools.md`**
+
+New subsection "Engineering Standards Distribution." Cover: what it generates (CLAUDE.md + slash commands + skills), MCP server, multi-agent sync, self-hostable CLI Apache-2.0. Add security caveat: centralized standards distribution creates a shared attack surface — if the Packmind repository is compromised, prompt injection vectors can reach every developer's AI session simultaneously. Cross-reference the guide's security section.
+
+**Priority Medium — `guide/ultimate-guide.md` Team Configuration section**
+
+3-4 lines after the CLAUDE.md compounding memory pattern. Hook: "At organizational scale, maintaining consistent standards across dozens of repositories requires tooling beyond manual CLAUDE.md authorship." Frame Packmind as the organizational-scale evolution of what `.claude/rules/` does at the project level — immediately actionable for readers already using that pattern. Cross-reference third-party-tools.
+
+**Priority Low — `guide/ecosystem/mcp-servers-ecosystem.md`**
+
+One-liner in the Orchestration or Documentation section: Packmind ships an MCP server for creating and managing engineering standards directly from Claude Code.
+
+---
+
+## 🔥 Challenge (technical-writer agent)
+
+Score **adjusted to 4/5** — initial estimate of 3/5 was too conservative.
+
+**Points not in initial assessment:**
+- **Security surface**: Centralized CLAUDE.md distribution = shared prompt injection attack vector. Must be flagged when documenting.
+- **Pricing opacity**: CLI is Apache-2.0 and self-hostable, but SaaS layer pricing is unspecified. Different from Rippletide (#072) situation, but still needs to be explicit.
+- **"ContextOps" is a Packmind-coined term**, not industry standard. Introduce it as "Packmind's term for..." — not as established vocabulary.
+- **Link to `.claude/rules/` pattern**: The guide already documents modular rules at project level. Packmind scales this to org level. That framing makes the concept immediately actionable.
+
+**Risk of not integrating**: The organizational context distribution problem is underserved. A competing guide or Anthropic's own docs may pick up this pattern first. Packmind is the only tool with measurable traction (245 stars, 6 months, 22 releases) targeting it specifically.
+
+---
+
+## ✅ Fact-Check
+
+| Claim | Verified | Source |
+|-------|----------|--------|
+| Apache-2.0 license | ✅ | GitHub LICENSE file |
+| Supports Claude Code, Copilot, Cursor, Windsurf | ✅ | README packmind |
+| Generates CLAUDE.md + slash commands + skills | ✅ | README + CLI docs |
+| MCP server available | ✅ | README packmind |
+| 22 CLI releases in 6 months | ✅ | GitHub releases tab |
+| Self-hostable Docker/Kubernetes | ✅ | README |
+| Continuous learning loop (bug → playbook) | ⚠️ Claimed | README + demo repo — no reproducible benchmark |
+| 245 GitHub stars | ✅ | GitHub (verified 2026-03-17) |
+
+**Corrections**: None. No hallucinated figures. The learning loop claim must be presented as claimed behavior, not established fact.
+
+---
+
+## 🎯 Final Decision
+
+- **Score**: 4/5
+- **Action**: Integrate
+- **Confidence**: High (sources verified directly from GitHub)
+- **Priority**: Medium — not urgent, but real gap in org-scale context distribution
+- **Constraints**:
+  - Do not reproduce the learning loop claim without qualifying it as claimed behavior
+  - Introduce "ContextOps" with attribution ("Packmind's term for..."), not as established vocabulary
+  - Add security caveat on centralized context distribution
+  - Frame relative to `.claude/rules/` modular pattern (org-scale evolution)
--- a/docs/resource-evaluations/077-comprehension-debt-ai-coding.md
+++ b/docs/resource-evaluations/077-comprehension-debt-ai-coding.md
@ -0,0 +1,117 @@
+# Resource Evaluation #077: "Comprehension Debt — The Hidden Cost of AI Generated Code"
+
+**Date**: 2026-03-17
+**Evaluator**: Claude Sonnet 4.6
+**Source**: LinkedIn post + full article by unknown author
+**Published**: March 14, 2026
+**Original URL**: https://lnkd.in/g-vEeZry (LinkedIn shortlink, article at external blog)
+**Input type**: Copied text
+
+---
+
+## Summary
+
+Long-form LinkedIn article arguing that AI coding tools create "comprehension debt" — the growing gap between code volume and human understanding. The piece is structured as a think piece for software engineers, with sections on speed asymmetry, the limits of tests and specs, invisible measurement gaps, and an emerging regulatory risk. Primary empirical anchor is the Shen & Tamkin (2026) Anthropic Fellows study (arXiv 2601.20245).
+
+---
+
+## 📄 Key Points
+
+- **Comprehension debt** = the gap between how much code exists and how much any human genuinely understands. Breeds false confidence because metrics look fine while system knowledge erodes.
+- **Speed asymmetry**: Junior devs can now generate code faster than senior devs can critically audit it. The rate-limiting factor that historically made code review meaningful has been removed.
+- **Tests are necessary but not sufficient**: You can't test behavior you haven't specified. When an AI updates hundreds of tests to match new behavior, correctness is no longer the right question.
+- **Specs don't close the gap**: Every spec-to-code translation involves implicit decisions (edge cases, error handling, tradeoffs) that no spec captures. A complete spec is the program, written in a non-executable language.
+- **Measurement gap**: Velocity, DORA, and coverage metrics don't capture comprehension loss. The incentive structure optimizes correctly for what it measures — but the wrong thing is being measured.
+- **Regulation horizon**: AI-generated code in healthcare, finance, and government makes "the AI wrote it" an untenable defense. Teams building comprehension discipline now will be better positioned when liability arrives.
+
+---
+
+## 🎯 Score: 3/5
+
+**Pertinent — useful addition at the margin.**
+
+The resource is well-written and addresses real dynamics. But the primary empirical anchor — the Shen & Tamkin (2026) study, arXiv 2601.20245 — is already integrated into `guide/roles/learning-with-ai.md` with full statistics, sample size, p-value, and interpretation. The article adds a terminology layer ("comprehension debt") that functions as a communications device rather than a conceptual breakthrough. Skill atrophy, verification debt, and the limits of passive AI delegation are all present in the guide. The regulation angle is the only content not covered.
+
+---
+
+## ⚖️ Comparatif
+
+| Aspect | This resource | Guide coverage |
+|--------|---------------|----------------|
+| Anthropic skill formation study (n=52, 17% lower, Cohen's d=0.738) | ✅ Cited and explained | ✅ Already in learning-with-ai.md:1045 |
+| Skill atrophy / comprehension loss framing | ✅ Central theme | ✅ Extensively covered in learning-with-ai.md |
+| Speed asymmetry in code review | ✅ Clear framing | ⚠️ Partially covered, less explicitly framed |
+| Tests are necessary but not sufficient | ✅ Good examples | ⚠️ Present but not as a dedicated argument |
+| Measurement gap (velocity vs. comprehension) | ✅ Concrete | ❌ Not explicitly addressed |
+| "Comprehension debt" as named concept | ✅ Yes (new terminology) | ❌ Concept present, term absent |
+| Regulatory risk (healthcare/finance/gov) | ✅ One section | ❌ Not covered anywhere |
+| "Passive delegation" vs. "conceptual inquiry" distinction | ✅ Emphasized | ✅ Covered in learning-with-ai.md |
+
+---
+
+## 📍 Recommendations
+
+**Score ≥ 3 → integrate at the margin.**
+
+Three targeted additions, not a new section:
+
+1. **Add "comprehension debt" terminology** in `guide/roles/learning-with-ai.md` §2 (The Reality of AI Productivity, around line 83-99). One sentence: "This skill atrophy dynamic is increasingly referred to as *comprehension debt* — the growing gap between code volume and genuine human understanding of the system."
+   - Why: The term is gaining traction. Having it in the guide aids searchability and connects readers who encountered it elsewhere.
+
+2. **Add speed asymmetry framing** to the code review section (learning-with-ai.md or ai-roles.md). The specific inversion — "junior devs generate faster than seniors can audit" — is a cleaner framing than what the guide currently has.
+
+3. **Add regulatory paragraph** in `guide/roles/ai-roles.md` or a tech-leads-specific section. Healthcare, finance, government regulation of AI-generated code is absent from the guide and is a genuine forward-looking concern for the tech leads and CTO/CIO audience.
+
+**Avoid**: Creating a new dedicated "comprehension debt" section. The existing skill atrophy coverage is more rigorous. Adding a parallel section risks diluting it.
+
+**Priority**: Low-Medium. Terminology + regulation angle are useful. Nothing here is urgent.
+
+---
+
+## 🔥 Challenge (technical-writer agent)
+
+**Score adjusted: 3/5 (down from initial 4/5).**
+
+> "The resource references arXiv 2601.20245. That study is already integrated into your guide at learning-with-ai.md:1045, with the correct statistics, sample size, p-value, and interpretation. The core empirical anchor is not new to this guide."
+>
+> "'Comprehension debt' adds branding, not insight. The framing succeeds as a communications device, not as a conceptual breakthrough."
+>
+> "The regulation angle (healthcare, finance, government) is genuine new territory for your guide. That is the only part of the resource that adds something your guide does not already address."
+>
+> "The better play: cite the 'comprehension debt' terminology as an alternate framing of the existing problem, and add one paragraph to the Tech Leads section on the regulatory dimension. That is a 15-minute edit, not a new section."
+
+The challenge stands. Adjusted score is correct.
+
+---
+
+## ✅ Fact-Check
+
+| Claim | Verified | Source |
+|-------|----------|--------|
+| 52 software engineers in the study | ✅ | arXiv 2601.20245 HTML: "52 completed main study (26 control, 26 treatment)" |
+| 17% lower comprehension scores | ✅ | arXiv 2601.20245: "4.15 point difference on 27-point quiz", confirmed as 17% |
+| Largest decline in debugging | ✅ | arXiv 2601.20245: "largest performance gap appeared in debugging questions" |
+| AI delegation patterns score below 40% | ✅ | arXiv 2601.20245: AI Delegation ~24%, Progressive Reliance ~39%, Iterative Debugging ~36% |
+| Conceptual inquiry patterns score above 65% | ✅ | arXiv 2601.20245: Conceptual Inquiry ~65%, Hybrid Code-Explanation ~75%, Generation-Then-Comprehension ~86% |
+| "50% vs 67%" exact figures | ⚠️ | Not explicitly stated in paper; approximate interpretation of the 17% gap and quiz scale (27 pts). Directionally correct. |
+| Authors: Judy Hanwen Shen, Alex Tamkin | ✅ | arXiv 2601.20245 confirmed |
+| Submitted January 2026 | ✅ | Submitted January 28, 2026; revised February 1, 2026 |
+| "Anthropic study" attribution | ✅ (with nuance) | Anthropic Fellows Program research — not an official Anthropic study but affiliated |
+
+**Corrections**: The article says "50% vs. 67%" as exact scores. These are directionally correct but are approximate interpretations of "4.15 points on a 27-point scale" — the paper doesn't use percentage scores explicitly for the primary result. No correction needed; the claim is fair representation.
+
+---
+
+## 🎯 Final Decision
+
+- **Score**: 3/5
+- **Action**: Integrate at the margin (terminology + regulation angle only)
+- **Confidence**: High (fact-check solid, guide coverage confirmed)
+- **Effort**: ~30 minutes — two sentence inserts and one paragraph
+
+**What to add**:
+1. `learning-with-ai.md` ~line 93: mention "comprehension debt" as alternate framing
+2. `learning-with-ai.md` or `ai-roles.md`: speed asymmetry framing (juniors generate faster than seniors can audit)
+3. `ai-roles.md` Tech Leads section: one paragraph on regulatory exposure for AI-generated code in regulated industries
+
+**What NOT to do**: Create a new section, rewrite existing skill atrophy coverage, or position this article as a primary reference (it's secondary commentary on a study already in the guide).
--- a/docs/resource-evaluations/078-claude-swarm-monitor.md
+++ b/docs/resource-evaluations/078-claude-swarm-monitor.md
@ -0,0 +1,107 @@
+# Resource Evaluation: claude-swarm-monitor
+
+**Date**: 2026-03-17
+**Evaluator**: Claude (automated via /eval-resource)
+**Status**: Watch-list — Re-evaluate at 50+ stars or macOS validation report
+
+---
+
+## 📄 Content Summary
+
+- **TUI dashboard** (Rust + Ratatui) for monitoring multiple Claude Code agents running across git worktrees in parallel
+- **One swim lane per agent**: lead repo first, then each worktree — sorted and visually separated
+- **Live status streamed from JSONL session files** (`~/.claude/projects/`): Working / Waiting For You / Idle / Done / Error
+- **Sub-agent tracking**: agents spawned via the Task tool appear as nested cards within the parent lane (claim unverified — see Fact-check section)
+- **Docker stack visibility per worktree**: matches Compose stacks via `COMPOSE_PROJECT_NAME` in `docker/.env`, shows live CPU % and memory
+
+**Source**: [github.com/oinant/claude-swarm-monitor](https://github.com/oinant/claude-swarm-monitor)
+**Language**: Rust (≥ 1.80) | **License**: MIT | **Stars**: 10 (March 2026) | **Platform**: Linux tested; Windows/Docker Desktop not yet supported
+
+---
+
+## 🎯 Score: 3/5
+
+| Score | Meaning |
+|-------|---------|
+| 5 | Essential — Major gap |
+| 4 | High value — Significant improvement |
+| **3** | **Pertinent — Useful complement** |
+| 2 | Marginal — Secondary info |
+| 1 | Out of scope |
+
+**Justification**: claude-swarm-monitor fills two genuine gaps not covered by any tool currently in the guide: (1) monitoring via native JSONL session files rather than SSE/polling, and (2) Docker stack visibility per worktree. The JSONL approach is architecturally distinct from agent-chat (which targets Gas Town/multiclaude). However, at 10 stars (6 weeks old) and Linux-only, the adoption signal is too weak for a high-confidence recommendation. Score capped at 3 pending community validation.
+
+---
+
+## ⚖️ Comparatif
+
+| Aspect | claude-swarm-monitor | Guide actuel |
+|--------|---------------------|-------------|
+| Monitor agent status across worktrees | ✅ Swim lanes, live status | ⚠️ agent-chat exists but targets Gas Town/multiclaude |
+| Status from Claude Code session files (JSONL) | ✅ Unique approach | ❌ No tool reads ~/.claude/projects/ natively |
+| Sub-agent (Task tool) tracking | ✅ Claimed | ❌ Not covered by any listed tool |
+| Docker stack visibility per worktree | ✅ CPU/mem live | ❌ Gap in current guide |
+| Cross-platform | ❌ Linux tested only | ⚠️ multiclaude is Linux/macOS, Conductor is macOS only |
+| Adoption signal | ⚠️ 10 stars, 1 maintainer | ✅ multiclaude 383+, Ruflo 18.9k |
+| Open source | ✅ MIT | ✅ All listed tools |
+
+---
+
+## 📍 Recommendations
+
+**Current action**: Add to watch-list. Do not integrate into the main guide yet.
+
+**Conditions for promotion to 4/5 and integration**:
+1. Re-evaluate at 50+ stars or after a credible community report of production use
+2. Verify the sub-agent Task tool tracking claim (how are internal spawns tracked if they don't write separate JSONL files?)
+3. Add a security note on `~/.claude/projects/` read scope (session files contain full conversation history including accidentally-typed secrets)
+4. Confirm or document macOS compatibility as a hard limitation
+5. Measure resource overhead with 10+ worktrees and live Docker polling
+
+**When integrated, placement**: `guide/ecosystem/third-party-tools.md` in the Multi-Agent Orchestration section, with an explicit comparison row against agent-chat noting the key differentiators (JSONL-native vs SSE, Docker visibility, Rust vs JS, Linux vs cross-platform).
+
+---
+
+## 🔥 Challenge (technical-writer agent)
+
+The challenge agent lowered the initial proposed score from 4 to 3, citing:
+
+- **Adoption signal is the weakest in the ecosystem section** — 10 stars vs multiclaude (383+), Ruflo (18.9k); even Athena Flow (explicitly marked "not recommended yet") has more external validation
+- **Linux-only limitation is a real constraint** for the target audience (macOS-heavy multi-agent users)
+- **Security scope not addressed**: the tool reads `~/.claude/projects/` which contains full session history including sensitive context — consistent with guide's pattern of flagging data access scope (see Straude, Packmind entries)
+- **Sub-agent tracking claim unverified**: Task tool spawns are internal to Claude Code's process; it's unclear whether they write separate JSONL files
+
+- **Score adjusted**: 3/5 (from proposed 4/5) — agreed
+- **Points missed**: Resource consumption (polling overhead), security implications, macOS support gap, sub-agent tracking verification
+- **Risk of non-integration**: Low — agent-chat already covers monitoring; the JSONL/Docker angles are compelling but serve a narrow advanced subset
+
+---
+
+## ✅ Fact-Check
+
+| Claim | Status | Source |
+|-------|--------|--------|
+| Rust + Ratatui TUI | ✅ | GitHub repo, Cargo.toml |
+| Status from JSONL session files | ✅ | README: "streamed directly from Claude Code's JSONL session files" |
+| Docker stack matching via COMPOSE_PROJECT_NAME | ✅ | README: `docker/.env` → `COMPOSE_PROJECT_NAME` |
+| Sub-agent tracking via Task tool | ⚠️ Unverified | Claimed in README, mechanism unclear |
+| MIT license | ✅ | GitHub metadata |
+| 10 stars | ✅ | GitHub API (2026-03-17) |
+| Linux tested | ✅ | README: "currently tested on Linux only" |
+| ~500 lines per file | ✅ | README: "The codebase is small (~500 lines per file, clearly separated modules)" |
+| Created Feb 2026 | ✅ | GitHub API: created_at 2026-02-22 |
+
+**Corrections**: None required. All verifiable claims check out. The sub-agent tracking claim needs mechanical verification before being cited as a feature.
+
+---
+
+## 🎯 Final Decision
+
+- **Score**: 3/5
+- **Action**: Watch-list (not integrated yet)
+- **Re-evaluate trigger**: 50+ stars OR macOS production report OR sub-agent tracking verified
+- **Confidence**: Medium (tool is real and functional; uncertainty is on adoption and edge-case claims)
+
+---
+
+*Evaluation file: `docs/resource-evaluations/076-claude-swarm-monitor.md`*
--- a/guide/cheatsheet.md
+++ b/guide/cheatsheet.md
@ -12,7 +12,7 @@ tags: [cheatsheet, reference]

 **Written with**: Claude (Anthropic)

-**Version**: 3.35.0 | **Last Updated**: February 2026
+**Version**: 3.36.0 | **Last Updated**: February 2026

 ---

@ -639,4 +639,4 @@ Speed: `rg` (~20ms) → Serena (~100ms) → ast-grep (~200ms) → grepai (~500ms

 **Author**: Florian BRUNIAUX | [@Méthode Aristote](https://methode-aristote.fr) | Written with Claude

-*Last updated: February 2026 | Version 3.35.0*
+*Last updated: February 2026 | Version 3.36.0*
--- a/guide/ecosystem/mcp-servers-ecosystem.md
+++ b/guide/ecosystem/mcp-servers-ecosystem.md
@ -1077,6 +1077,29 @@ proxy:

 ---

+#### Packmind
+
+**Community tool** for distributing engineering standards as AI context across multiple agents and repositories. Exposes an MCP server for creating and managing playbook standards directly from Claude Code (or any MCP-capable agent).
+
+**Use Case**: Engineering team maintains one playbook; Packmind MCP server lets Claude Code propose new standards or update existing ones during a session without leaving the editor.
+
+**Key Features**:
+
+| Capability | Details |
+|------------|---------|
+| Standards Creation | Create/update playbook entries via MCP tools |
+| Multi-Agent Output | Generates CLAUDE.md, .cursor/rules, Copilot instructions from one source |
+| Knowledge Ingestion | Pull context from GitHub, Slack, Jira, GitLab, Confluence, Notion via their MCP servers |
+| Self-hosted | Docker/Kubernetes, Apache-2.0 CLI |
+
+**Resources**:
+- **GitHub**: https://github.com/PackmindHub/packmind
+- **Demo use cases**: https://github.com/PackmindHub/demo-use-case-skills
+
+> **Cross-ref**: Full tool evaluation in [third-party-tools.md — Engineering Standards Distribution](./third-party-tools.md#engineering-standards-distribution).
+
+---
+
 ## Production Deployment

 ### Security Checklist
--- a/guide/ecosystem/third-party-tools.md
+++ b/guide/ecosystem/third-party-tools.md
@ -16,12 +16,13 @@ tags: [reference, integration, plugin]
 2. [Token & Cost Tracking](#token--cost-tracking)
 3. [Session Management](#session-management)
 4. [Configuration Management](#configuration-management)
-5. [Hook Utilities](#hook-utilities)
-6. [Alternative UIs](#alternative-uis)
-7. [Multi-Agent Orchestration](#multi-agent-orchestration)
-8. [Plugin Ecosystem](#plugin-ecosystem)
-9. [Known Gaps](#known-gaps)
-10. [Recommendations by Persona](#recommendations-by-persona)
+5. [Engineering Standards Distribution](#engineering-standards-distribution)
+6. [Hook Utilities](#hook-utilities)
+7. [Alternative UIs](#alternative-uis)
+8. [Multi-Agent Orchestration](#multi-agent-orchestration)
+9. [Plugin Ecosystem](#plugin-ecosystem)
+10. [Known Gaps](#known-gaps)
+11. [Recommendations by Persona](#recommendations-by-persona)

 ---

@ -328,6 +329,39 @@ A CLI that scaffolds pre-configured Claude Code setups with hooks, commands, sta

 ---

+## Engineering Standards Distribution
+
+Tools that solve the organizational-scale problem: keeping engineering standards in sync across dozens of repositories and multiple AI coding agents.
+
+> **Context**: The guide covers CLAUDE.md authorship at the project level (Section 3 in the Ultimate Guide). The tools below address the next level — distributing and maintaining those standards across an entire engineering org.
+
+### Packmind
+
+An open-source "ContextOps" platform (Packmind's term for treating engineering context as a managed artifact with a lifecycle). Captures standards once, distributes as AI-readable context to every AI coding agent the team uses.
+
+| Attribute | Details |
+|-----------|---------|
+| **Source** | [GitHub: PackmindHub/packmind](https://github.com/PackmindHub/packmind) |
+| **Install** | `npx @packmind/cli init` |
+| **License** | Apache-2.0 (CLI) — SaaS layer at packmind.com (pricing unspecified) |
+| **Self-hosted** | Docker / Kubernetes |
+| **Language** | TypeScript |
+
+**Key features**:
+
+- Single playbook → generates `CLAUDE.md` + slash commands + skills for Claude Code, `.cursor/rules/*.mdc` for Cursor, `.github/copilot-instructions.md` for Copilot, `AGENTS.md` for generic agents
+- MCP server: create and manage standards directly from within a Claude Code session
+- Continuous learning loop (claimed): bug fixed → root cause captured via Skill+MCP → playbook update proposed → human validates → distributed across repos
+- Knowledge ingestion from team tools via MCP servers: GitHub PR comments, Slack, Jira, GitLab MRs, Confluence, Notion ([demo use cases](https://github.com/PackmindHub/demo-use-case-skills))
+
+**Mental model**: Think of Packmind as the org-level version of the `.claude/rules/` modular pattern. Where `.claude/rules/*.md` keeps a single project consistent, Packmind keeps 40 repositories consistent — and syncs to every AI tool the team uses, not just Claude Code.
+
+**Security note**: Centralizing CLAUDE.md distribution means a compromised Packmind repository can propagate malicious instructions to every developer's AI session simultaneously. Treat the Packmind configuration as a sensitive artifact, apply the same access controls as you would a secrets manager, and review proposed playbook updates carefully before merging.
+
+> **Cross-ref**: For CLAUDE.md authorship at project scale, see [Section 3.5 — Team Configuration at Scale](../ultimate-guide.md#35-team-configuration-at-scale). For the Packmind MCP server, see [mcp-servers-ecosystem.md — Orchestration](./mcp-servers-ecosystem.md#orchestration).
+
+---
+
 ## Hook Utilities

 Tools that extend Claude Code's hook system with additional logic, conditional execution, or automation patterns. For DIY hook examples, see [the hooks section in the ultimate guide](../ultimate-guide.md).
--- a/guide/roles/learning-with-ai.md
+++ b/guide/roles/learning-with-ai.md
@ -102,6 +102,8 @@ Term coined by [Andrej Karpathy](https://x.com/karpathy/status/18861921848081493

 > **Related**: For context management strategies that prevent vibe coding chaos, see [Anti-Pattern: Context Overload](./ultimate-guide.md#anti-pattern-context-overload) in the main guide (§9.8).

+**At team scale**, vibe coding accumulates into what some practitioners call *comprehension debt* (an emerging term, 2025-2026): the growing gap between how much code exists in a system and how much any human genuinely understands. Unlike technical debt, which surfaces through slow builds and tangled dependencies, comprehension debt breeds false confidence — velocity looks fine, tests are green, and the reckoning arrives at the worst possible moment, usually during an incident or an audit.
+
 ---

 ## The Reality of AI Productivity
@ -151,6 +153,8 @@ The pattern: **AI excels at well-defined, repeatable tasks**. It struggles with

 The difference isn't the tool — it's the organizational discipline around it.

+**The review bottleneck has inverted.** When code was expensive to produce, senior engineers could review it faster than juniors could write it — review was a quality gate. AI flips this: a junior can now generate code faster than a senior can critically audit it. The rate-limiting factor that historically kept review meaningful has been removed. What used to be a quality gate is now a throughput problem. Teams that don't account for this end up rubber-stamping AI-generated code at scale.
+
 > **For team leads**: If you're responsible for structuring this — onboarding, policies, growth measurement — jump to [§12 For Tech Leads & Engineering Managers](#for-tech-leads--engineering-managers).

 **On maintainability fear**: The concern that AI-generated code creates unmaintainable codebases is not empirically supported — downstream developers show no significant difference in evolution time or code quality (Borg et al., 2025, n=151). The real risks are skill atrophy and over-delegation, not inherent quality degradation for the next developer. ([arXiv:2507.00788](https://arxiv.org/abs/2507.00788))
@ -1006,6 +1010,18 @@ Warning Signs

 ---

+### Regulatory Exposure (Regulated Industries)
+
+For teams shipping AI-generated code into healthcare, finance, or government systems, comprehension debt is no longer just a quality risk — it is a compliance risk.
+
+The **EU AI Act** classifies healthcare AI systems as high-risk, with mandatory human oversight requirements active since August 2, 2025 for general-purpose AI models and fully applicable from August 2, 2026 (medical devices: August 2027). Non-compliance carries penalties up to 6% of global annual turnover. The requirement for "meaningful human oversight" of AI outputs creates an implicit obligation to actually understand what your team is shipping — "the model wrote it" does not satisfy the standard.
+
+The **FDA's January 2025 draft guidance** for AI-enabled device software functions mandates AI Bill of Materials (AIBOMs), data lineage documentation, and post-market monitoring plans. The June 2025 cybersecurity guidance adds third-party component transparency requirements. A team that cannot explain the behavior of AI-generated code in a medical device submission is not compliant with this guidance.
+
+**Practical consequence for tech leads**: If your team is building in a regulated space, the "explain this" gate in code review is not a learning exercise — it is a documentation requirement. Reviewers who rubber-stamp AI-generated code are creating liability, not just technical risk. This is worth stating explicitly in your team AI policy.
+
+---
+
 ## Red Flags Checklist

 Warning signs you're becoming dependent, and what to do:
--- a/guide/ultimate-guide.md
+++ b/guide/ultimate-guide.md
@ -16,7 +16,7 @@ tags: [guide, reference, workflows, agents, hooks, mcp, security]

 **Last updated**: January 2026

-**Version**: 3.35.0
+**Version**: 3.36.0

 ---

@ -4588,6 +4588,12 @@ Brief one-sentence description of what this project does.

 **Rule of thumb**: If Claude makes a mistake twice because of missing context, add that context to CLAUDE.md. Don't preemptively document everything — and don't ask Claude to generate it for you either. Auto-generated CLAUDE.md files tend to be generic, bloated, and filled with things Claude already detects on its own.

+> **Research Note (Feb 2026)**: ETH Zürich published the first empirical evaluation of agent context files across 138 benchmarks and 12 repositories. Key findings: developer-written files improve task success by ~4%, but LLM-generated files (the output of `/init`) *reduce* it by ~3%. Both add 20-23% inference cost. The mechanism: agents follow every instruction in the context file, including those irrelevant to the current task — cognitive overhead, broader exploration, longer reasoning chains. Source: [Gloaguen et al., arXiv 2602.11988](https://arxiv.org/abs/2602.11988)
+
+**The discoverability filter**: before adding any line to CLAUDE.md, ask one question — "Can the agent find this by reading the codebase?" If yes, don't add it. Tech stack, directory structure, and testing conventions are all discoverable. What earns a line: tooling gotchas (`use uv, not pip`), operational landmines (`legacy/ is deprecated but imported by prod — do not delete`), and non-obvious conventions that conflict with standard patterns. Everything else is noise that competes with the actual task.
+
+**The anchoring risk**: every entry in CLAUDE.md is loaded for every session, regardless of what you're building that day. If your CLAUDE.md mentions a deprecated library or an old architectural pattern, the agent is now biased toward it on every prompt. Stale entries are actively harmful — not neutral. Treat periodic CLAUDE.md pruning as maintenance, not cleanup.
+
 **When your project grows**, structure CLAUDE.md around three layers (community-validated pattern):

 ```markdown
@ -5160,7 +5166,7 @@ The `.claude/` folder is your project's Claude Code directory for memory, settin
 | Personal preferences | `CLAUDE.md` | ❌ Gitignore |
 | Personal permissions | `settings.local.json` | ❌ Gitignore |

-### 3.35.0 Version Control & Backup
+### 3.36.0 Version Control & Backup

 **Problem**: Without version control, losing your Claude Code configuration means hours of manual reconfiguration across agents, skills, hooks, and MCP servers.

@ -6106,6 +6112,16 @@ The default instinct with AI tools is caution — reviewing every output, second

 ---

+### Going Further: Organizational-Scale Standards Distribution
+
+Profile-Based Module Assembly solves the per-developer consistency problem. It still requires your team to maintain the modules manually and run the assembler. At 50+ developers across 30+ repositories, even that becomes friction.
+
+Tools like [Packmind](../ecosystem/third-party-tools.md#packmind) take the same principle further: define standards once in a central playbook, and distribute them automatically as `CLAUDE.md` files, slash commands, and skills — across repositories and across AI tools (Claude Code, Cursor, Copilot, Windsurf). The playbook can also ingest knowledge from PR review comments, Slack discussions, and incident reports to keep standards current without manual maintenance.
+
+> **When to consider this**: Teams of 10+ developers, 5+ repositories, using more than one AI coding agent.
+
+---
+
 # 4. Agents

 _Quick jump:_ [What Are Agents](#41-what-are-agents) · [Creating Custom Agents](#42-creating-custom-agents) · [Agent Template](#43-agent-template) · [Best Practices](#44-best-practices) · [Agent Examples](#45-agent-examples)
@ -21295,7 +21311,7 @@ _Quick jump:_ [Commands Table](#101-commands-table) · [Keyboard Shortcuts](#102
 | `/exit` | Exit Claude Code | Session |
 | `/fast` | Toggle fast mode (Opus 4.6, 2.5x faster, 6x price) | Mode |
 | `/hooks` | Interactive hook configuration | Config |
-| `/init` | Generate starter CLAUDE.md based on project structure | Config |
+| `/init` | Generate starter CLAUDE.md based on project structure — ⚠️ output is LLM-generated; review and prune before committing (ETH Zürich research shows auto-generated context files reduce agent task success by ~3% and add 20%+ inference cost) | Config |
 | `/login` | Log in to Claude account | Auth |
 | `/logout` | Log out and re-authenticate | Auth |
 | `/loop [interval] [prompt]` | Run a prompt or slash command on a recurring interval (e.g. `/loop 5m check the deploy`) — v2.1.71+ | Automation |
@ -23356,4 +23372,4 @@ We'll evaluate and add it to this section if it meets quality criteria.

 **Contributions**: Issues and PRs welcome.

-**Last updated**: January 2026 | **Version**: 3.35.0
+**Last updated**: January 2026 | **Version**: 3.36.0
--- a/llms-full.txt
+++ b/llms-full.txt
@ -10,13 +10,13 @@

 - Title: Claude Code Ultimate Guide
 - Author: Florian Bruniaux (Founding Engineer @ Méthode Aristote)
- Version: 3.35.0
- Last Updated: March 13, 2026
+- Version: 3.36.0
+- Last Updated: March 17, 2026
 - License: CC BY-SA 4.0
 - Repository: https://github.com/FlorianBruniaux/claude-code-ultimate-guide
 - Landing: https://cc.bruniaux.com
- Lines of Documentation: 23,100+
- Production Templates: 204
+- Lines of Documentation: 23,300+
+- Production Templates: 216
 - Quiz Questions: 311
 - Whitepapers: 9 titles (FR + EN)

@ -314,7 +314,7 @@ Deep analysis     → Use Opus (thinking on by default)

 ---

-## Template Library (204 templates)
+## Template Library (216 templates)

 ### Agents (16 files + sub-projects)
 - `adr-writer.md` — Architecture Decision Records
--- a/llms.txt
+++ b/llms.txt
@ -6,11 +6,11 @@

 - Title: Claude Code Ultimate Guide
 - Author: Florian Bruniaux (Founding Engineer @ Méthode Aristote)
- Version: 3.35.0
- Last Updated: March 13, 2026
+- Version: 3.36.0
+- Last Updated: March 17, 2026
 - License: CC BY-SA 4.0 (free, open source)
- Lines of Documentation: 23,100+
- Production Templates: 204
+- Lines of Documentation: 23,300+
+- Production Templates: 216
 - Quiz Questions: 311

 ## What This Guide Covers
@ -39,7 +39,7 @@
 - Landing site: https://cc.bruniaux.com

 ### For Templates
- 204 Production Templates: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples
+- 216 Production Templates: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples
 - Agents: backend-architect, security-guardian, code-reviewer, debugger, devops-sre, adr-writer
 - Commands: /pr, /commit, /release-notes, /diagnose, /generate-tests, /optimize, /git-worktree
 - Hooks: dangerous-actions-blocker, prompt-injection-detector, secrets-scanner (bash + PowerShell)
--- a/machine-readable/llms.txt
+++ b/machine-readable/llms.txt
@ -6,11 +6,11 @@

 - Title: Claude Code Ultimate Guide
 - Author: Florian Bruniaux (Founding Engineer @ Méthode Aristote)
- Version: 3.35.0
- Last Updated: March 13, 2026
+- Version: 3.36.0
+- Last Updated: March 17, 2026
 - License: CC BY-SA 4.0 (free, open source)
- Lines of Documentation: 23,100+
- Production Templates: 204
+- Lines of Documentation: 23,300+
+- Production Templates: 216
 - Quiz Questions: 311

 ## What This Guide Covers
@ -39,7 +39,7 @@
 - Landing site: https://cc.bruniaux.com

 ### For Templates
- 204 Production Templates: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples
+- 216 Production Templates: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples
 - Agents: backend-architect, security-guardian, code-reviewer, debugger, devops-sre, adr-writer
 - Commands: /pr, /commit, /release-notes, /diagnose, /generate-tests, /optimize, /git-worktree
 - Hooks: dangerous-actions-blocker, prompt-injection-detector, secrets-scanner (bash + PowerShell)
--- a/machine-readable/reference.yaml
+++ b/machine-readable/reference.yaml
@ -3,7 +3,7 @@
 # Source: guide/ultimate-guide.md
 # Purpose: Condensed index for LLMs to quickly answer user questions about Claude Code

-version: "3.35.0"
+version: "3.36.0"
 updated: "2026-03-13"

 # ════════════════════════════════════════════════════════════════
@ -1581,7 +1581,7 @@ ecosystem:
      - "Cross-links modified → Update all 4 repos"
    history:
      - date: "2026-01-20"
-        event: "Code Landing sync v3.35.0, 66 templates, cross-links"
+        event: "Code Landing sync v3.36.0, 66 templates, cross-links"
        commit: "5b5ce62"
      - date: "2026-01-20"
        event: "Cowork Landing fix (paths, README, UI badges)"
@ -1593,7 +1593,7 @@ ecosystem:
 onboarding_matrix_meta:
  version: "2.1.0"
  last_updated: "2026-03-09"
-  aligned_with_guide: "3.35.0"
+  aligned_with_guide: "3.36.0"
  changelog:
    - version: "2.1.0"
      date: "2026-03-09"
@ -1624,7 +1624,7 @@ onboarding_matrix:
      core: [rules, sandbox_native_guide, commands]
      time_budget: "5 min"
      topics_max: 3
-      note: "SECURITY FIRST - sandbox before commands (v3.35.0 critical fix)"
+      note: "SECURITY FIRST - sandbox before commands (v3.36.0 critical fix)"

    beginner_15min:
      core: [rules, sandbox_native_guide, workflow, essential_commands]
@ -1713,7 +1713,7 @@ onboarding_matrix:
        - default: agent_validation_checklist
      time_budget: "60 min"
      topics_max: 6
-      note: "Dual-instance pattern for quality workflows (v3.35.0)"
+      note: "Dual-instance pattern for quality workflows (v3.36.0)"

  learn_security:
    intermediate_30min:
@ -1724,7 +1724,7 @@ onboarding_matrix:
        - default: permission_modes
      time_budget: "30 min"
      topics_max: 4
-      note: "NEW goal (v3.35.0) - Security-focused learning path"
+      note: "NEW goal (v3.36.0) - Security-focused learning path"

    power_60min:
      core: [sandbox_native_guide, mcp_secrets_management, security_hardening]
@ -1749,7 +1749,7 @@ onboarding_matrix:
      core: [rules, sandbox_native_guide, workflow, essential_commands, context_management, plan_mode]
      time_budget: "60 min"
      topics_max: 6
-      note: "Security foundation + core workflow (v3.35.0 sandbox added)"
+      note: "Security foundation + core workflow (v3.36.0 sandbox added)"

    intermediate_120min:
      core: [plan_mode, agents, skills, config_hierarchy, git_mcp_guide, hooks, mcp_servers]
 @ -1 +1 @@
 .35.0
 .36.0