Florian BRUNIAUX
|
dacba17ea6
|
docs(eval): add Rippletide Code evaluation #081 + watch-list entry
Score 3/5. Hook-native runtime rule enforcement via PreToolUse hooks and
Context Graph. Addresses CLAUDE.md degradation at scale (40+ rules) and
compaction-driven rule loss. Free beta (npx rippletide-code, no signup).
Distinct from eval 072 (Rippletide MCP/SaaS platform). Multiple performance
claims unverified (compaction-resistance, 5s build time, 50% stat). Privacy
surface unaddressed (external convention extraction). Watch trigger: public
GitHub >100 stars or independent practitioner write-up.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-03-17 21:29:54 +01:00 |
|
Florian BRUNIAUX
|
8e63d84b47
|
docs: factual audit + reference sync — 260 findings corrected
Parallel 6-agent audit against official Anthropic docs (llms-full.txt).
Key corrections applied across permissions, hooks, MCP, security, privacy, reference.yaml.
Highlights:
- Fix MCP config path (~/.claude.json), mcpServers key, variable substitution syntax
- Fix permission modes (5 not 3), :* syntax (×6), Stop event description
- Fix hook JSON field names (hook_event_name, tool_name, tool_input, session_id)
- Fix filesystem restriction docs (permission rules, not settings.json keys)
- Fix data-privacy: 4-tier retention, /bug 5yr warning, ZDR conditions, 5 telemetry opt-out vars
- Add official llms.txt/llms-full.txt references to CLAUDE.md + machine-readable/llms.txt
- Reference.yaml: 375 entries re-synced (92% had wrong line numbers — guide grew 15K→21K lines)
- New script: scripts/resync-reference-yaml.py for automated line number sync
- Quiz: corrected answers for hooks (07), memory settings (03), MCP servers (08)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-02-26 12:10:14 +01:00 |
|
Florian BRUNIAUX
|
6117145837
|
docs: integrate veille hebdo Anthropic 17-23 fev 2026 (+177 lignes guide)
P1 - Prompt caching + env vars:
- Strategy 6 cost optimization: cache_control API, pricing (write 1.25x, read 0.1x), break-even 2 hits
- CLAUDE_CODE_DISABLE_1M_CONTEXT + CLAUDE_CODE_SIMPLE ajoutés à la table env vars principale
P2 - Model deprecations + agents:
- Warning claude-3-haiku-20240307 deprecated 19 fev / retirement 20 avril 2026
- Frontmatter fields: background: true (v2.1.49+) + isolation: worktree (v2.1.50+)
- Section Background Agents: comportement non-blocking, gestion (ctrl+f, double ESC)
- Section claude agents CLI: commande + output annoté
P3 - Worktree isolation native + security cross-ref:
- Native worktree features: --worktree flag, isolation declaratif, WorktreeCreate/WorktreeRemove hooks
- §7.4 Security Hooks: cross-ref Claude Code Security scanner (research preview)
Eval: docs/resource-evaluations/2026-02-22-veille-hebdo-anthropic-17-23-fev.md (score 3/5)
Stats: 19K → 20K lignes (20 440 total)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-02-23 12:59:28 +01:00 |
|
Florian BRUNIAUX
|
d1182af4cf
|
docs: v3.27.1 — fact-check corrections, grepai docs, RTK overhaul
Fact-check (README positioning):
- Template count: 120/123 → 108 (ground truth recount)
- Ratio: 14× → 24× (19,000 ÷ 784 = 24.2×)
- everything-cc stars: 31.9k → 45k+ (verified Feb 15)
- Commands count: 20 → 23, hooks: 30 → 31
Added:
- Grepai MCP documentation (semantic search, call graphs)
- 3 hook templates (rtk-baseline, session-summary, session-summary-config)
- 2 resource evaluations (system-prompts update, qmd token savings)
Changed:
- RTK documentation overhaul (v0.7.0 → v0.16.0, rtk-ai org)
- Exports deprecated (kimi.pdf, notebooklm.pdf → deprecated/)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-02-15 18:41:45 +01:00 |
|
Florian BRUNIAUX
|
d72905e9ba
|
docs: integrate Entire CLI across guide (v3.27.0)
Major integration of Entire CLI, an agent-native platform launched
Feb 2026 by Thomas Dohmke (ex-GitHub CEO) with $60M funding. Provides
rewindable checkpoints, approval gates, and audit trails for AI sessions.
## Added (7 guide files + 3 meta files)
- **ai-traceability.md**: Replace git-ai 404 with Entire CLI (section 5.1)
- **third-party-tools.md**: Fill "Session replay" gap + add tool section
- **observability.md**: Add session portability alternative
- **ai-ecosystem.md**: Add governance-first orchestration (section 8.1.5)
- **ultimate-guide.md**: Enrich multi-instance section 9.17
- **security-hardening.md**: Add compliance audit trails (section 3.4)
- **cheatsheet.md**: Add Community Tools quick reference
- **README.md**: Update structure tree with third-party-tools mention
- **CHANGELOG.md**: Document v3.27.0 release
- **docs/resource-evaluations/entire-cli.md**: Formal evaluation (5/5)
## Fixed
- git-ai references (404 repo) replaced with working alternative
- "Session replay" Known Gap now marked as ✅ FILLED
## Key Features Documented
- Rewindable checkpoints (prompts + reasoning + tool usage)
- Governance layer (approval gates, permissions, audit trails)
- Multi-agent handoffs (Claude → Gemini with context)
- Compliance-ready (SOC2, HIPAA, FedRAMP)
- Session portability (path-agnostic vs native --resume)
## Positioning
- vs git-ai: Replaces non-existent tool (404)
- vs claude-code-viewer: Active replay vs read-only history
- vs Gas Town: Governance sequential vs parallel coordination
Files modified: 10 (7 content + 3 meta)
Words added: ~2,500
Version: 3.26.0 → 3.27.0
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
|
2026-02-12 23:33:16 +01:00 |
|