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-boostgit 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-boost)<a href="https://agentmods.dev/skills/bidiche49/claude-conf/claude-md-boost"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/claude-md-boost/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-boost"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/claude-md-boost.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 | $0.00020 | $0.00667 |
| Opus 5 | $0.00010 | $0.00333 |
| Sonnet 5 | $0.00004 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
claude-md-boost 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rewrite the project CLAUDE.md as a CTO and prompt engineering expert. Every line must measurably change Claude's behavior. 20 precise lines > 100 lines of filler.
Process
-
If no CLAUDE.md exists → tell the user to run
/claude-md-initfirst. Stop. -
Cleanup phase (integrated — don't ask the user to run cleanup separately):
- Read project CLAUDE.md and
~/.claude/CLAUDE.md - Identify installed modules (markers:
<!-- critical-thinking:start -->,<!-- backlog:start -->, etc.) - Remove duplicates with global config (same rules as
/claude-md-cleanup)
- Read project CLAUDE.md and
-
Explore the project:
- Directory structure, config files, stack detection
- Read 4-6 representative code files (handler, service, model, test, config)
- Identify real patterns, naming conventions, error handling style
-
Analyze the current CLAUDE.md — for each rule, ask:
- Is it actionable? (can you verify compliance in a code review?)
- Does it come from real code or is it generic filler?
- Are build/test commands the real ones from config files?
- Is anything critical for this stack missing?
-
Rewrite the CLAUDE.md:
- Preserve the user's intent (what they wanted to express)
- Make every rule specific and actionable
- Add stack-specific conventions detected in the code (with BON/MAUVAIS examples from real code)
- Structure in optimal order: Projet → Regles → Build & Test → Architecture → Conventions → Config → Etat actuel
Stack best practices to check for (only add what's actually used in the project):
iOS/Swift : weak self in closures, deinit cleanup, navigation patterns, force unwrap rules, concurrency (actors/async-await) React/Next : hooks rules (deps arrays), component patterns (server vs client), state management, SSR boundaries Node/Express : error handling middleware, async/await patterns, validation layer, env config Flutter : widget lifecycle, state management (Riverpod/Bloc/Provider), platform channels, key usage Go : error handling (wrap vs return), goroutine patterns, interface design, table-driven tests Python : type hints, async/await, test fixtures, dependency injection patterns Rust : ownership patterns, Result/Option handling, trait design, test organization PHP/Laravel : service pattern, Eloquent conventions, form requests, middleware -
Present the diff — show old vs new for each section that changed, with rationale.
-
Wait for explicit validation before writing.
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 · 53 lines · 20 tokens per session scan A d6ab66dc49a2
claude-md-boost is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 667 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.
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…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.
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.