claude-md

claude-md is a skill for Claude Code from poshan0126/dotclaude. It costs 48 tokens per session (823 once invoked), scanned A, original, MIT.

A workflow for keeping CLAUDE.md, a project instruction file loaded for developers, accurate and brief. It either records durable lessons from the current session or audits the file for outdated commands, drift, and excess content.

In plain words
What is it for?
Use it after a session to record lessons that prevent repeat mistakes, or use audit mode to compare the file with the project’s current reality.
Why use it?
It helps prevent useful project knowledge from being lost while keeping instructions from becoming stale or bloated.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Good fit Use it after a session to record lessons that prevent repeat mistakes, or use audit mode to compare the file with the project’s current reality.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/poshan0126/dotclaude/claude-md
Install

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.

Any agent
npx skills add poshan0126/dotclaude --skill claude-md
Clone the repo
git clone --depth 1 https://github.com/poshan0126/dotclaude

Made for: Claude Code.

Wrote 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.

agentmods badge for claude-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/poshan0126/dotclaude/claude-md/github.svg)](https://agentmods.dev/skills/poshan0126/dotclaude/claude-md)
Your own site
<a href="https://agentmods.dev/skills/poshan0126/dotclaude/claude-md"><img src="https://agentmods.dev/badge/skills/poshan0126/dotclaude/claude-md/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.

agentmods 80×15 button for claude-md

Your own site · 80×15
<a href="https://agentmods.dev/skills/poshan0126/dotclaude/claude-md"><img src="https://agentmods.dev/badge/skills/poshan0126/dotclaude/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 823 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00823
Opus 5 $0.00024 $0.00411
Sonnet 5 $0.00010 $0.00165
Haiku 4.5 $0.00005 $0.00082

Measured 9d ago against content hash ee82bb1d4740, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-md 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.

skills/claude-md/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md loads every turn for every developer; this skill is how it earns that. Two modes: default captures learnings from the current session; audit checks the whole file against reality.

Capture (default)

Scan THIS conversation for durable, project-level learnings. A learning qualifies only if ALL of these hold:

  • It would prevent a repeat mistake. The user corrected you, a command failed in a non-obvious way, or a constraint surprised you.
  • It's not derivable from the code. Claude can re-discover file structure and signatures; it can't re-discover "the staging DB is the one named prod_replica".
  • It's durable. True next month, not just this task. Session-specific state belongs in /catchup handoff, not here.
  • It's not already covered by CLAUDE.md, a rule in .claude/rules/, or enforced by a hook.

For each qualifying learning (usually 0-3 per session — finding none is a fine outcome):

  1. Draft it as ONE line, with the why if it isn't obvious: Use \make test-fast` for iteration — `make test` spins up Docker (3 min).`
  2. Pick its destination: command fixes → Commands section; constraints with a path scope → suggest a path-scoped rule instead; everything else → the matching CLAUDE.md section.
  3. If it contradicts an existing line, propose editing that line, not appending a second truth.

Present all candidates with AskUserQuestion (multiSelect — let the user pick which to keep), then apply only the selected ones.

Audit (when $ARGUMENTS contains audit)

Check every line of CLAUDE.md against reality:

  1. Commands: does each documented command still exist (package.json scripts, Makefile targets, etc.) and match its description? Run --help/--dry-run variants where cheap.
  2. Paths and names: do referenced directories, files, and tools still exist?
  3. Duplication: lines that repeat .claude/rules/ content, hook-enforced behavior, or standard conventions Claude already knows — propose deletion.
  4. Leftovers: any > REPLACE: template blocks — propose deletion.
  5. Staleness candidates: claims contradicted by recent code (cross-check anything that smells off against the source).

Read the full file on GitHub · 51 lines

Changes

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.

  1. 9d ago First seen · 51 lines · 48 tokens per session scan A ee82bb1d4740

Subscribe to this mod's changes

claude-md is a skill published in the GitHub repository poshan0126/dotclaude (860 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 823 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens