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 martineserios/thebrana --skill claudemdgit clone --depth 1 https://github.com/martineserios/thebranaWrote 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/martineserios/thebrana/claudemd)<a href="https://agentmods.dev/skills/martineserios/thebrana/claudemd"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/claudemd/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/martineserios/thebrana/claudemd"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/claudemd.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 | $0.00034 | $0.02774 |
| Opus 5 | $0.00017 | $0.01387 |
| Sonnet 5 | $0.00007 | $0.00555 |
| Haiku 4.5 | $0.00003 | $0.00277 |
Grade A, and why
claudemd 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 6d 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claudemd — Audit or Generate CLAUDE.md
Two modes:
- audit (default if CLAUDE.md exists): Read existing file, flag bloat and misplaced content, propose a leaner version.
- generate (default if no CLAUDE.md): Interview the user and produce a lean CLAUDE.md from scratch.
When to use
- User wants to create a CLAUDE.md for a new project
- Existing CLAUDE.md has grown bloated or Claude is ignoring parts of it
- User wants to know what belongs in CLAUDE.md vs rules/, skills/, or hooks/
- After
/brana:onboardsurfaces that no CLAUDE.md exists - After
/brana:alignon brownfield projects — to clean up bloat from F2 appending.
Mode routing
Parse the first argument:
auditoraudit <path>→ run Audit flowgenerateorgenerate <path>→ run Generate flow- No argument → check if
./CLAUDE.mdor./.claude/CLAUDE.mdexists → if yes, Audit; if no, Generate
Audit Flow
Step 1: READ
Read the CLAUDE.md at the given path (default: ./CLAUDE.md, then ./.claude/CLAUDE.md).
Also read any files it imports (@path syntax).
Note total line count.
Step 2: CLASSIFY
For each line/block, classify into one of:
| Category | Keep in CLAUDE.md? | Better home |
|---|---|---|
| Project identity (one-liner, stack) | ✅ Yes | — |
| Commands CC can't guess (non-standard build/test/lint) | ✅ Yes | — |
| Code style that differs from language defaults | ✅ Yes | — |
| Architectural decisions specific to this project | ✅ Yes | — |
| Env var requirements, non-obvious setup quirks | ✅ Yes | — |
| Branch naming, PR conventions (team-specific) | ✅ Yes | — |
| Known gotchas, non-obvious behaviors | ✅ Yes | — |
| Standard language conventions CC already knows | ❌ Delete | nowhere — it's noise |
| Detailed API docs or long tutorials | ❌ Delete | link to external docs |
| Task-specific workflows (only relevant sometimes) | ❌ Move | .claude/skills/ (preferred) or .claude/commands/ (legacy) |
| "Always X" behavioral rules | ❌ Move | .claude/rules/ (use YAML frontmatter paths: to scope) |
| Deterministic enforcement (must happen every time) | ❌ Move | hooks |
| File-by-file codebase descriptions | ❌ Delete | let CC read the code |
| Frequently-changing information | ❌ Delete | MEMORY.md or task context |
| Anything CC infers correctly without it | ❌ Delete | it's redundant |
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.
- 6d ago First seen · 300 lines · 34 tokens per session scan A b645bdd35064
claudemd is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 2,774 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
init-workspace-context
Classify workspace mode.
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
check-docs-consistency
Cross-reference project docs for drift, stale references, and contradictions. Outputs timestamped report. Discovers Markdown wherever it lives in the repo.
release-init
Detect project type and generate a tailored project-level /release skill. Run once per project to set up releasing.
eu-ai-act-check
EU AI Act compliance — migrated to pitimon/claude-governance v3.1.0. This stub redirects to the canonical implementation. Maps to H1 (Be Proactive — prevent regulatory crisis) + H8 (Voice/Conscience).