claude-md

claude-md is a skill for Claude Code from sp-daewoon/chronicle. It costs 72 tokens per session (347 once invoked), scanned A, original, MIT.

A maintenance workflow for an existing CLAUDE.md file, which gives coding agents project instructions. It checks the file against the current codebase and keeps only accurate, useful guidance.

In plain words
What is it for?
Updating build, test, lint, architecture, and convention notes while removing stale or duplicated content.
Why use it?
Project instructions can become outdated as commands, folders, and coding practices change, causing agents to follow incorrect or unnecessary rules.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the chronicle plugin — 6 skills, 6 commands shipped together

Good fit Updating build, test, lint, architecture, and convention notes while removing stale or…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sp-daewoon/chronicle/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 sp-daewoon/chronicle --skill claude-md
Clone the repo
git clone --depth 1 https://github.com/sp-daewoon/chronicle

Made for: Claude Code.

Or install chronicle, the plugin that ships this one along with the rest of its 6 skills, 6 commands.

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/sp-daewoon/chronicle/claude-md.svg)](https://agentmods.dev/skills/sp-daewoon/chronicle/claude-md)
Your own site
<a href="https://agentmods.dev/skills/sp-daewoon/chronicle/claude-md"><img src="https://agentmods.dev/badge/skills/sp-daewoon/chronicle/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 347 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.
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 $0.00072 $0.00347
Opus 5 $0.00036 $0.00173
Sonnet 5 $0.00014 $0.00069
Haiku 4.5 $0.00007 $0.00035

Measured 7d ago against content hash faacea5e2e5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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 · 32 lines

What it actually says

CLAUDE.md Maintenance Workflow

Keep an existing CLAUDE.md accurate and lean. This is for ongoing upkeep — use the built-in /init for first creation.

Process

  1. Read the current CLAUDE.md.
  2. Compare against reality: recent commits, changed build commands, new/removed modules, updated conventions, new architecture decisions (check the ADR directory).
  3. Update only the affected sections. Do not rewrite untouched sections.
  4. Prune: remove stale instructions, merge duplicates, and keep each section tight. If a section has grown long, tighten it rather than letting it sprawl.
  5. Preserve the user's voice and structure — you are maintaining their file, not replacing it.

What to check for drift

  • Build / test / lint commands that changed
  • Module or directory structure changes
  • New conventions or rules the team adopted
  • Architecture decisions recorded as ADRs that belong in the high-level guidance
  • Anything now contradicted by the actual codebase

Rules

  • Never blow away existing content wholesale — edit surgically.
  • Keep it scannable; CLAUDE.md is loaded into every session, so brevity matters.
  • If something is already obvious from the code or another doc, don't duplicate it here.
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. 7d ago First seen · 32 lines · 72 tokens per session scan A faacea5e2e5c

Subscribe to this mod's changes

claude-md is a skill published in the GitHub repository sp-daewoon/chronicle (4 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 347 once invoked, about $0.0004 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.

Related

Other skills, from other repositories