readme-update

readme-update is a skill for Claude Code, Codex from momentmaker/kaijutsu. It costs 82 tokens per session (1,327 once invoked), scanned A, original, MIT.

A repository checker that finds signs that a project’s README—the file explaining how to install and use the project—may no longer match the code.

In plain words
What is it for?
It reviews the README’s last update, examines later commits and changed files, and suggests which README sections may need targeted updates.
Why use it?
It helps catch documentation that has fallen behind after changes, so users are less likely to follow outdated installation, usage, or public API instructions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It reviews the README’s last update, examines later commits and changed files, and suggests which README sections may need targeted updates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/momentmaker/kaijutsu/readme-update
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 momentmaker/kaijutsu --skill readme-update
Clone the repo
git clone --depth 1 https://github.com/momentmaker/kaijutsu

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-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/momentmaker/kaijutsu/readme-update.svg)](https://agentmods.dev/skills/momentmaker/kaijutsu/readme-update)
Your own site
<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/readme-update"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/readme-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,327 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 $0.00082 $0.01327
Opus 5 $0.00041 $0.00664
Sonnet 5 $0.00016 $0.00265
Haiku 4.5 $0.00008 $0.00133

Measured 8d ago against content hash be1f67e3192d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

readme-update 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 8d 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/community/readme-update/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

readme-update

Most READMEs decay silently. This skill catches the decay early by anchoring on the last commit that touched README.md, walking forward, and matching what changed against which README sections are likely affected.

Step 1: Find the README

Look for, in order:

  • README.md at the repo root
  • README.MD, Readme.md, readme.md (case variants)

If multiple Markdown files plausibly serve as the README (e.g., docs/README.md), ask the user which one to update.

Step 2: Find the Last Update

LAST_SHA=$(git log -n 1 --format="%H" -- README.md)
LAST_DATE=$(git log -n 1 --format="%ad" --date=iso -- README.md)

If LAST_SHA is empty, the README has never been committed. In that case, ask the user "should I generate a fresh README from scratch?" and stop here.

Step 3: List Commits Since

git log "${LAST_SHA}..HEAD" --format="%h %s"
git diff --name-only "${LAST_SHA}..HEAD"

If the list is empty, report "README is up to date with HEAD (last touched )" and stop.

Step 4: Categorize the Changes

Bucket the changed files into themes:

Theme File patterns README sections likely affected
Dependencies package.json, go.mod, Cargo.toml, pyproject.toml, requirements.txt, Gemfile, composer.json Installation, Prerequisites
Build / scripts package.json scripts, Makefile, justfile, Taskfile.yml, .github/workflows/* Build, Development, CI
CLI / binaries new files under cmd/, bin/, src/cli/, executable shell scripts Usage, Examples
Public API exported symbols, route handlers, OpenAPI specs, generated SDKs API, Reference
Configuration .env.example, config schemas, settings files Configuration
Schema / data migration files, prisma/sqlx schemas, GraphQL SDL Schema, Data Model
Docs links docs/** additions or renames Documentation, Further Reading

Step 4.5: Check badges + image staleness

While scanning, audit:

  • Version badges in the README header — does the version match the latest tag? Latest release? Latest published package?
  • License badges — match LICENSE file?
  • Build / lint badges — link still valid? Workflow still exists?
  • Embedded images / diagrams — mtime newer or older than the related code's mtime? An out-of-date architecture diagram is often worse than no diagram.

Read the full file on GitHub · 119 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 119 lines · 82 tokens per session scan A be1f67e3192d

Subscribe to this mod's changes

readme-update is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,327 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.