Commit graph

7 commits

Author SHA1 Message Date
Florian BRUNIAUX
5b713db6fd feat(mcp): add official Anthropic docs tracker — v1.1.0
New tools (4):
- init_official_docs()    — fetch + store baseline + current snapshots locally
- refresh_official_docs() — update current without touching baseline
- diff_official_docs()    — compare baseline vs current, 0 network, section-level
- search_official_docs(query) — search official docs, loads only matching sections

Architecture:
- 4 local cache files in ~/.cache/claude-code-guide/ (index + content, baseline + current)
- Diff reads index files only (~50KB each), never the full 1.2MB content
- search loads only matched sections from content file (not entire doc)
- Atomic writes (.tmp + rename) prevent snapshot corruption
- schemaVersion: 1 for future-proof migrations

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-11 17:28:25 +01:00
Florian BRUNIAUX
ff11f7566b fix(mcp): correct releases GitHub URL (guide/core/ path)
Wrong path guide/claude-code-releases.md → guide/core/claude-code-releases.md in 3 tools (changelog, releases, compare-versions). Was generating 404 links in get_digest output.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-11 14:49:47 +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
Florian BRUNIAUX
0d70fd88f0 feat(seo): GEO optimization — llms.txt v3.32.2, llms-full.txt, FAQ
Phase 1 (repo): update machine-readable/llms.txt (v3.8.0→3.32.2,
87→238 templates, 9.6K→22.7K lines), create root llms.txt per
llmstxt.org convention, create llms-full.txt (~20KB: cheatsheet,
template list, FAQ), sync mcp-server/content/llms.txt.

Phase 4 (README): replace invisible HTML keyword comment with visible
mini-FAQ (5 Q&A) for GEO crawlers.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-09 14:15:35 +01:00
Florian BRUNIAUX
01283fafec docs: SonnetPlan hack — budget Sonnet+Haiku hybrid via env var remap
- guide/ultimate-guide.md §OpusPlan: new "Budget Variant: SonnetPlan"
  section with shell function, Plan/Act routing table, caveat on
  unreliable model self-report, link to GitHub issue #9749
- examples/scripts/sonnetplan.sh: new ready-to-use shell function
  with installation instructions and verification guidance

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 17:58:25 +01:00
Florian BRUNIAUX
67ea720d63 fix(mcp): correct content path + publish 1.0.3
Fix ENOENT on production install: CONTENT_DIR resolved 2 levels up
from dist/ instead of 1, reaching node_modules/ instead of package
root where content/ lives. ../content is the correct relative path.

Publié : claude-code-ultimate-guide-mcp@1.0.3

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-28 21:26:57 +01:00
Florian BRUNIAUX
7236362c1e feat(mcp): add 4 new tools — compare_versions, get_threat, list_threats, search_examples
New tools (8 → 12 total):
- compare_versions(from, to): diff Claude Code releases between two versions,
  aggregating highlights and breaking changes across the range
- get_threat(id): look up any CVE or attack technique (T-code) with full details,
  severity, mitigation, and source references
- list_threats(category?): browse the threat database — summary table or
  detailed view by section (cves, authors, skills, techniques, mitigations, sources)
- search_examples(query, limit?): semantic search across 199 templates with
  token-aware scoring and get_example() hints

Infrastructure:
- content.ts: add loadThreatDb() with memory cache and dual-mode loading
  (GUIDE_ROOT filesystem in dev, GitHub fetch in production)
- Threat DB interface with correct Record<string, string> type for minimum_safe_versions

Docs:
- mcp-server/README.md: document all 12 tools with usage examples
- mcp-server/IDEAS.md: future ideas (quiz, methodology, workflow, diff resource)
- CHANGELOG.md: [Unreleased] entry for all 4 tools
- README.md: promote MCP section to standalone ## after Quick Start (was ### inside Quick Start)
- guide/architecture.md: add MCP server to Extended Tool Ecosystem

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-28 19:22:20 +01:00