marketing-shibata50/claude-code-ultimate-guide
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
448 commits 1 branch 0 tags 20 MiB
Commit graph

11 commits

Author SHA1 Message Date
Florian BRUNIAUX
043eb796f0 docs: update Claude Code releases to v2.1.79 
- --console flag for claude auth login (Anthropic Console / API billing)
- Show turn duration toggle in /config menu
- VSCode /remote-control command + AI-generated session tab titles
- Fixed claude -p hanging without explicit stdin
- Fixed enterprise 429 retry and SessionEnd hooks on /resume switch
- ~18MB startup memory improvement

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-19 11:58:52 +01:00
Florian BRUNIAUX
eea5662a65 docs: update Claude Code releases to v2.1.78 
- Update latest tracked version: v2.1.77 → v2.1.78
- Add v2.1.78 highlights: StopFailure hook, ${CLAUDE_PLUGIN_DATA}
  persistent plugin state, streaming line-by-line, 3 security fixes
  (silent sandbox disable, MCP deny rules bypass, protected dirs in
  bypassPermissions mode)
- Update CHANGELOG with release tracking entry

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-18 15:08:33 +01:00
Florian BRUNIAUX
1bbf346687 docs: update Claude Code releases to v2.1.77 
- Opus 4.6 default max output raised to 64k tokens; upper bound 128k
- Security fix: PreToolUse hooks bypass of enterprise deny rules
- allowRead sandbox setting, /branch command, /copy N shorthand
- Breaking: Agent tool resume param removed (use SendMessage instead)
- Fixed auto-updater memory leak; fixed --resume history truncation

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-17 08:42:20 +01:00
Florian BRUNIAUX
da8bc09f2d feat: smart-suggest ROI script + hook tuning + guide updates (Mar 16) 
- Add examples/scripts/smart-suggest-roi.py: stdlib-only analyzer correlating
  suggestion log with session JSONL files to measure command acceptance rate.
  4 acceptance signals, tier breakdown, daily trend, --json/--since/--no-sessions CLI.
- Tune Aristote smart-suggest hook: tighten 5 over-firing triggers (/tech:commit,
  /tech:sonarqube, /tech:dupes, /check-conventions a11y, /tech:worktree)
- Guide: identity re-injection hook, context engineering maturity grid, code review
  workflow, 1M context window GA update, Spring Break promo, security audit patterns
- Resource evaluations: Nick Tune hooks (3/5), VicKayro security audit (2/5),
  Karl Mazier CLAUDE.md templates, Paul Rayner ContextFlow, Siddhant agent trace,
  Andrew Yng context hub, JP Caparas 1M context window

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-16 12:20:40 +01:00
Florian BRUNIAUX
30e3916eb3 docs: update Claude Code releases to v2.1.76 
- MCP elicitation: servers request structured input mid-task via interactive dialog
- New hooks: Elicitation, ElicitationResult, PostCompact
- -n/--name CLI flag for session display name at startup
- worktree.sparsePaths for monorepo sparse checkout; /effort slash command
- Fixed ToolSearch deferred tools losing input schemas after compaction
- Auto-compact circuit breaker (stops after 3 consecutive failures)
- Fixed Bash(cmd:*) rules not matching when quoted argument contains #

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-14 18:44:21 +01:00
Florian BRUNIAUX
0d31b8ff77 docs: update Claude Code releases to v2.1.75 
- Update latest tracked version: 2.1.74 → 2.1.75
- Highlights: 1M context Opus 4.6 default for Max/Team/Enterprise, session name on prompt bar, hook source in permission prompts, token estimation over-counting fix, Bash ! mangling fix
- Updated: 2026-03-13

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-13 19:32:04 +01:00
Florian BRUNIAUX
b6ce1ef72f docs: add RPI workflow, changelog fragments, smart-suggest hook + LLM variance 
- guide/workflows/rpi.md (new): Research → Plan → Implement, 3-phase pattern
  with explicit GO gates, slash command templates, worked example
- guide/workflows/changelog-fragments.md (new): per-PR YAML fragment enforcement,
  3-layer system (CLAUDE.md rule + UserPromptSubmit hook + CI gate)
- examples/hooks/bash/smart-suggest.sh (new): UserPromptSubmit behavioral coach,
  3-tier priority (enforcement/discovery/contextual), ROI logging
- guide/core/known-issues.md: LLM Day-to-Day Performance Variance section,
  4 root causes (probabilistic inference, MoE routing, infra, context sensitivity)
- guide/workflows/README.md: added RPI entry + quick selection row
- machine-readable/reference.yaml: added entries for changelog_fragments, smart_suggest
- CHANGELOG.md: [Unreleased] entries for all 4 new items
- IDEAS.md: prompt-caching MCP plugin research note (testing in progress)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-13 16:22:57 +01:00
Florian BRUNIAUX
27352cc455 docs: update Claude Code releases to v2.1.74 
- v2.1.74: /context actionable suggestions, autoMemoryDirectory setting,
  streaming buffer memory leak fix, managed policy ask rules bypass fix,
  SessionEnd hook timeout now configurable
- v2.1.73: modelOverrides setting, skill hot-reload deadlock fix, subagent
  model downgrade fix on Bedrock/Vertex/Foundry, Opus 4.6 default on 3P,
  /output-style deprecated in favor of /config

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-12 10:28:54 +01:00
Florian BRUNIAUX
4dd479161d docs: update Claude Code releases to v2.1.72 
- Update latest tracked version: 2.1.71 → 2.1.72 (2026-03-09)
- Agent model parameter restored on Agent tool for per-invocation overrides
- SDK query() prompt cache fix — up to 12x input token cost reduction
- CLAUDE.md HTML comments now hidden from Claude when auto-injected
- Simplified effort levels: low/medium/high, new symbols ○ ◐ ●
- ExitWorktree tool + CLAUDE_CODE_DISABLE_CRON env var + /plan optional desc
- Bump guide version: 3.34.1 → 3.34.2

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-11 15:55:15 +01:00
Florian BRUNIAUX
fe28f89574 feat(context): Context Engineering Configurator + consolidated guide (v3.34.0) 
New: interactive configurator at cc.bruniaux.com/context/ that generates a
personalized CLAUDE.md starter kit based on team size, stack, and current setup.
Multi-step flow (profile, current state, stack, results) with maturity scoring
(Level 1-5), copy-to-clipboard artifacts, localStorage persistence.

Guide content:
- guide/core/context-engineering.md (1,188 lines, 8 sections): context budget,
  150-instruction ceiling, modular architecture, team assembly, ACE pipeline,
  quality measurement, context reduction techniques
- examples/context-engineering/ (10 templates): assembler.ts, profile-template.yaml,
  skeleton-template.md, canary-check.sh, ci-drift-check.yml, eval-questions.yaml,
  context-budget-calculator.sh, rules/knowledge-feeding.md, rules/update-loop-retro.md
- tools/context-audit-prompt.md (543 lines): 8-dimension scoring /100

Navigation: guide/README.md, machine-readable/reference.yaml (24 new entries)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-11 11:18:04 +01:00
Florian BRUNIAUX
b65630641b refactor(guide): restructure guide/ into thematic subdirectories 
Reorganize 22 guide files from a flat directory into 5 thematic subdirs:
- core/ (architecture, methodologies, known-issues, claude-code-releases, visual-reference)
- security/ (security-hardening, sandbox-isolation, sandbox-native, production-safety, data-privacy)
- ecosystem/ (ai-ecosystem, mcp-servers-ecosystem, third-party-tools, remarkable-ai)
- roles/ (ai-roles, adoption-approaches, learning-with-ai, agent-evaluation)
- ops/ (devops-sre, observability, ai-traceability)

All internal links updated across ~50 files (ultimate-guide.md, workflows/,
diagrams/, README.md, docs/, tools/, examples/, machine-readable/).

Also: merge search-tools-cheatsheet.md into cheatsheet.md, rewrite guide/README.md
with H2 grouped sections, update CLAUDE.md repository structure.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-10 08:35:13 +01:00