Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Bidiche49/claude-conf --skill claude-md-initgit clone --depth 1 https://github.com/Bidiche49/claude-confWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bidiche49/claude-conf/claude-md-init)<a href="https://agentmods.dev/skills/bidiche49/claude-conf/claude-md-init"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/claude-md-init/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bidiche49/claude-conf/claude-md-init"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/claude-md-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.00640 |
| Opus 5 | $0.00009 | $0.00320 |
| Sonnet 5 | $0.00004 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
claude-md-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate a project-specific CLAUDE.md by analyzing the real codebase. Every line must be actionable and specific to THIS project.
Process
-
Check if
CLAUDE.mdexists at project root. If yes, warn and ask confirmation before overwriting. -
Explore the project:
- Directory structure (top 2-3 levels)
- Config files: package.json, pubspec.yaml, go.mod, Cargo.toml, pyproject.toml, composer.json, Makefile, .xcodeproj, tsconfig.json, .eslintrc, etc.
git log --oneline -20for recent activity- Detect: stack, framework, ORM, test runner, linter, monorepo vs monolith
-
Read 4-6 representative files (controller, service, model, test, config) — pick files with real logic, not boilerplate.
-
Read
~/.claude/CLAUDE.mdto identify what's already covered globally (mindset, ticketing, handoff, critical-thinking, general rules). Do NOT duplicate any of it. -
Generate CLAUDE.md with this exact structure:
# CLAUDE.md — [Project Name]
## Projet
[2-3 lines: what it does, who it's for, main stack]
## Regles specifiques a ce projet
[Rules NOT in the global config — specific to THIS project]
[e.g. "Never run xcodebuild directly", "Prisma migrations must be generated, not hand-written"]
## Build & Test
[REAL commands read from package.json/Makefile/etc. — not guesses]
## Architecture
[Simplified directory structure + stack table (framework/lib/version)]
## Conventions code (ce projet)
[Patterns extracted from REAL code read in step 3]
[Use BON/MAUVAIS format with examples from the actual codebase]
## Configuration
[Env vars (not values), API endpoints, services, external deps]
## Etat actuel
[Active branches, next steps if detectable from git]
- Present the generated CLAUDE.md to the user. Explain key choices. Wait for explicit validation before writing the file.
Rules — NON-NEGOTIABLE
- NEVER write generic content. FORBIDDEN: "Write clean code", "Follow best practices", "Test before committing", "Use meaningful names" — all useless filler.
- NEVER duplicate the global CLAUDE.md — ticketing, handoff, mindset, critical-thinking, general rules are already there.
- Every rule must be actionable — if you can't verify compliance in a code review, don't add it.
- Conventions from real code only — if unsure, leave it out. Fewer specific lines > many generic lines.
- Build/test commands must be real — read from config files, never guess.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 60 lines · 18 tokens per session scan A 9ef8d93c7896
claude-md-init is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 640 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
atomic-wiki
Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.
review-pr
Perform a comprehensive code review of a pull request.