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 |
|