auto-readme

auto-readme is a skill for Claude Code, Codex from stephansama/packages. It costs 82 tokens per session (1,149 once invoked), scanned A, original, MIT.

A tool that fills in marked tables and lists in README files from project files such as package.json, action.yml, workspace settings, or Zod schemas. A monorepo is one repository containing multiple packages.

In plain words
What is it for?
Use it to generate workspace package tables, GitHub Action input tables, dependency tables, Zod schema references, and other supported README sections, manually, in CI, or before commits.
Why use it?
It keeps documented package, dependency, action-input, and schema information aligned with the source files, avoiding manual updates.

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/stephansama/packages/auto-readme
Any agent
npx skills add stephansama/packages --skill auto-readme
Clone the repo
git clone --depth 1 https://github.com/stephansama/packages

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 auto-readme

README.md
[![agentmods](https://agentmods.dev/badge/skills/stephansama/packages/auto-readme.svg)](https://agentmods.dev/skills/stephansama/packages/auto-readme)
Your own site
<a href="https://agentmods.dev/skills/stephansama/packages/auto-readme"><img src="https://agentmods.dev/badge/skills/stephansama/packages/auto-readme.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 1,149 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 $0.00082 $0.01149
Opus 5 $0.00041 $0.00575
Sonnet 5 $0.00016 $0.00230
Haiku 4.5 $0.00008 $0.00115

Measured 4d ago against content hash ddb53d469002, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-readme 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 4d 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.

core/auto-readme/skills/auto-readme/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

auto-readme

Keeps README files up to date by replacing content between HTML comment markers. Run manually, in CI, or as a pre-commit hook.

Comment syntax

<!-- ACTION_TYPE [options] start -->
<!-- ACTION_TYPE end -->

Content between markers is replaced on every run. Markers must be paired — every start needs a matching end.

Setup

pnpx @stephansama/auto-readme

Add configuration to package.json:

{
  "auto-readme": {
    "disableEmojis": false,
    "onlyShowPublicPackages": true
  }
}

Or use a standalone config file (.autoreadmerc.json, .config/autoreadmerc.ts, autoreadme.config.ts, etc.).

Core Patterns

Monorepo workspace table

<!-- WORKSPACE start -->
<!-- WORKSPACE end -->

Generates a table of all packages in the workspace with name, version badge, download badge, and description. Reads from the pnpm/npm workspace config.

GitHub Action inputs table

<!-- ACTION start -->
<!-- ACTION end -->

Place this comment in a README inside a directory that contains action.yml or action.yaml. Generates a table of action inputs with name, required, default, and description columns.

Package.json dependency table

<!-- PKG start -->
<!-- PKG end -->

Generates a table of dependencies and devDependencies from the nearest package.json. Pass path= to point to a different package.json:

<!-- PKG path="../other-package" start -->
<!-- PKG end -->

Zod schema reference table

<!-- ZOD path="./src/schema.js" start -->
<!-- ZOD end -->

Generates a markdown reference table from the default export of the given file using zod2md. The path= parameter is required and must point to a file with a zod schema as its default export.

Pre-commit hook (changed files only)

# .husky/pre-commit
auto-readme --changes

--changes (-g) only processes README files that are modified in the current git changeset. Use in pre-commit hooks to avoid re-processing the entire repo on every commit.

Read the full file on GitHub · 190 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. 4d ago First seen · 190 lines · 82 tokens per session scan A ddb53d469002

Subscribe to this mod's changes

auto-readme is a skill published in the GitHub repository stephansama/packages (5 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,149 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

opendia-harness

Install, configure, and troubleshoot OpenDia for Grok Build (and other MCP harnesses). Use when setting up the plugin, config.toml MCP entry, ports, extension disconnects, tool timeouts, or tunnel mode.

aeonfun/opendia · 52 tokens

opendia

Drive the user's real browser through OpenDia MCP (logged-in sessions, cookies, wallets, bookmarks, history). Use when automating Chrome/Firefox for social posts, form fills, multi-tab research, local webapp testing, or any task that needs the user's existing browser profile — not a disposable cloud browser.

aeonfun/opendia · 66 tokens

npm-security

Prevent JavaScript/TypeScript projects from supply-chain attacks across package managers like npm, pnpm, yarn, bun, and deno. Use whenever planning, installing, updating packages or configuring package managers.

bodadotsh/npm-security-best-practices · 43 tokens

frontmcp-extensibility

Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…

agentfront/frontmcp · 124 tokens

huly-cli

Operate Huly through the @firfi/huly-cli executable. Use when a coding agent needs to authenticate, switch Huly workspaces or projects, discover commands, query structured Huly data, or perform confirmed Huly mutations from a shell or automation workflow.

dearlordylord/huly-mcp · 56 tokens

censor_message

Automatically censor profanity in messages by replacing with asterisks.

glincker/glin-profanity · 16 tokens