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.
npx skills add tomzx/agents --skill create-readmegit clone --depth 1 https://github.com/tomzx/agentsWrote 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.
[](https://agentmods.dev/skills/tomzx/agents/create-readme)<a href="https://agentmods.dev/skills/tomzx/agents/create-readme"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-readme/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.
<a href="https://agentmods.dev/skills/tomzx/agents/create-readme"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-readme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.01186 |
| Opus 5.5 | $0.00011 | $0.00474 |
| Sonnet 5.5 | $0.00005 | $0.00237 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
create-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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write README
Produces a README.md for a project using a fixed template with centered header, badges, feature list, roadmap, and setup instructions.
Derives content from the codebase, existing configuration files, and any available context.
Prerequisites
- A project directory with source code, a license file, and a package manifest (e.g.,
go.mod,package.json,Cargo.toml,pyproject.toml) - If
$1is provided, use it as the project directory; otherwise use the current working directory
Steps
- Scan the project for metadata: repository name from git remote or directory name, license type, language/runtime version from the package manifest, storage or database dependencies, and platform targets.
- Determine a one-sentence description of the project from existing docs, the package manifest description, or by reading the main entry point.
- List features by scanning source directories, CLI commands, exported functions, and any existing documentation.
- Identify roadmap items from open GitHub issues, TODO comments, or stated goals in docs.
- Identify out-of-scope items by reading issue discussions, design docs, or the package manifest's stated purpose.
- Determine install steps from the package manifest, Makefile, or build scripts.
- Write the README following the output template exactly.
- Write the file to
README.mdin the project root. - Add an HTML comment
<!-- session_link: http://localhost:10000/?session=<id> -->as the first line of the file, using the current session ID from context. If no session ID is available, omit the comment.
Output Format
<h1 align="center">{repository}</h1>
<p align="center">
<strong>{one sentence description of the project}</strong>
</p>
<p align="center">
<a href="./LICENSE"><img src="https://img.shields.io/github/license/tomzxcode/{repository}" alt="License"></a>
<img src="https://img.shields.io/badge/{language}-{version}%2B-{color}" alt="{Language} {version}+">
<img src="https://img.shields.io/badge/platform-{platforms}-lightgrey" alt="Platform">
</p>
<p align="center">
<img src="screenshot.png" alt="{repository} Demo"/>
</p>
## What
{2-4 sentences explaining what the project is and what it does.}
## Why
{2-4 sentences explaining the motivation behind the project, the problem it solves, and why it exists.}
## Included
{bullet point list of features, one per line, using - prefix}
## Roadmap
{bullet point list of planned features, one per line, using - prefix}
## Out of Scope
{bullet point list of features explicitly not planned, one per line, using - prefix}
## Requirements
{List of system requirements needed to build and run the project. Include language version, OS, and any external dependencies.}
## Install
{Step-by-step installation instructions with code blocks for commands.}
## Getting Started
{Step-by-step guide to using the project after installation. Include code examples where applicable.}
## License
The code is licensed under the [MIT license](http://choosealicense.com/licenses/mit/). See [LICENSE](LICENSE).
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.
- 22d ago Changed c9dfd54b8f86
- 23d ago Changed · -4 lines f9dab5505c94
- 28d ago Changed · +1 lines eec19a3b4b17
- 2mo ago First seen · 130 lines · 27 tokens per session scan A ec11dd57c72e
create-readme is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 1,186 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…