readme-updater

readme-updater is a skill for Claude Code, Codex from luqiang-code/claude-code-skills. It costs 39 tokens per session (577 once invoked), scanned A, original, MIT.

A tool for keeping a project's README file aligned with its actual code and folder structure. A README is the document that explains how to set up and use a project.

In plain words
What is it for?
Use it to inspect the project, find mismatches in README sections, propose updates, apply approved changes, and check that the project still builds.
Why use it?
It helps prevent setup steps, scripts, feature lists, and dependency information from becoming outdated after code changes.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/luqiang-code/claude-code-skills/readme-updater
Any agent
npx skills add luqiang-code/claude-code-skills --skill readme-updater
Clone the repo
git clone --depth 1 https://github.com/luqiang-code/claude-code-skills

Made for: Claude Code, Codex.

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 readme-updater

README.md
[![agentmods](https://agentmods.dev/badge/skills/luqiang-code/claude-code-skills/readme-updater.svg)](https://agentmods.dev/skills/luqiang-code/claude-code-skills/readme-updater)
Your own site
<a href="https://agentmods.dev/skills/luqiang-code/claude-code-skills/readme-updater"><img src="https://agentmods.dev/badge/skills/luqiang-code/claude-code-skills/readme-updater.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.00577
Opus 5 $0.00019 $0.00289
Sonnet 5 $0.00008 $0.00115
Haiku 4.5 $0.00004 $0.00058

Measured 5d ago against content hash 8b1840f5eeac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

readme-updater 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 5d 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.

community-skills/readme-updater/SKILL.md · 75 lines

What it actually says

README Updater

Keep README.md in sync with the actual project state.

When to Use

  • README has outdated setup instructions
  • Project structure changed but README wasn't updated
  • Adding new features that should be documented in README
  • User mentions "update readme", "readme is outdated"

When NOT to Use

  • Writing a README from scratch (use /init for context first)
  • Minor typo fixes (just fix directly)

Workflow

  1. Scan the project: package.json, directory structure, config files
  2. Compare against current README sections:
    • Setup instructions: Are deps, env vars, build steps still correct?
    • Project structure: Does the directory tree match reality?
    • Features: Are new features listed?
    • Scripts: Are npm run scripts documented and current?
    • Tech stack: Dependencies match package.json?
    • Contributing: Link to CONTRIBUTING.md still works?
  3. List discrepancies found
  4. Propose updates section by section
  5. Apply approved changes
  6. Run npm run build or equivalent to verify project still works

What to Check

✓ Setup steps actually work (run them to verify)
✓ Environment variables match .env.example
✓ Script commands in README match package.json scripts
✓ Directory tree matches actual folder structure
✓ Tech stack badges/versions match package.json
✓ API examples match actual routes
✓ License matches LICENSE file
✓ Contributing link is not broken
✓ All links in README are not 404

Key Principles

  • README should be accurate, not aspirational — document what IS, not what WILL BE
  • Setup instructions must be copy-paste runnable
  • Don't remove content without confirming with user
  • Keep it concise — README is the entry point, not the full docs

Notes

  • Don't add emoji or decorative elements unless they already exist
  • Follow the existing README style and tone
  • If README is extremely long, suggest moving sections to a docs site
  • Always show a diff of proposed changes before applying
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. 5d ago First seen · 75 lines · 39 tokens per session scan A 8b1840f5eeac

Subscribe to this mod's changes

readme-updater is a skill published in the GitHub repository luqiang-code/claude-code-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 577 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 2026-08-31.