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 rfdiosuao/AgentSkill --skill craft-repository-readmegit clone --depth 1 https://github.com/rfdiosuao/AgentSkillWrote 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/rfdiosuao/agentskill/craft-repository-readme)<a href="https://agentmods.dev/skills/rfdiosuao/agentskill/craft-repository-readme"><img src="https://agentmods.dev/badge/skills/rfdiosuao/agentskill/craft-repository-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/rfdiosuao/agentskill/craft-repository-readme"><img src="https://agentmods.dev/badge/skills/rfdiosuao/agentskill/craft-repository-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 | $0.00088 | $0.01479 |
| Opus 5 | $0.00044 | $0.00740 |
| Sonnet 5 | $0.00018 | $0.00296 |
| Haiku 4.5 | $0.00009 | $0.00148 |
Grade A, and why
craft-repository-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 10d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Craft Repository README
Turn a repository into a clear, credible landing page. Base every claim, command, badge, and link on the actual project; visual polish must never outrun accuracy.
Choose the operating mode
- Use audit mode when the user asks for feedback only. Inspect and report; do not edit or publish.
- Use build mode when the user asks to create or improve the README. Edit the repository and validate the result.
- Use publish mode only when the user asks to commit, push, open a pull request, or update repository settings. Follow the repository's normal Git workflow.
1. Inspect the real project
Before drafting, inspect:
- Existing
README*, contribution, security, license, changelog, and deployment documents. - Package manifests, entry points, example environment files, test commands, screenshots, logos, and public URLs.
- Git remote, default branch, release tags, CI workflows, and hosting configuration.
- Repository-level instructions such as
AGENTS.mdorCONTRIBUTING.md.
Derive the product name, one-sentence value proposition, audience, supported platforms, install commands, run commands, and deployment story from evidence. If a material fact cannot be verified, omit it or label it clearly as planned.
2. Run a public-scope and security check
Treat README work as a release review. Before exposing details:
- Search tracked files and staged changes for API keys, private keys, tokens, passwords, cookies, internal hostnames, private IPs, and personal paths.
- Never paste secrets from local configuration, chat history, shell history, or deployment files.
- Link to
.env.example; never reproduce values from.env. - Confirm that screenshots, QR codes, names, and contact links are intentionally public.
- Preserve license, trademark, attribution, and third-party asset notices.
Stop and surface a concrete blocker if publication would expose sensitive material.
3. Design the story before the decoration
Write the README for this sequence:
What ships with it
3 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.
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.
- 10d ago First seen · 141 lines · 88 tokens per session scan A df0f33eb9a42
craft-repository-readme is a skill published in the GitHub repository rfdiosuao/AgentSkill (16 stars, last pushed 29d ago), licensed MIT. It adds 88 tokens to every session and 1,479 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 2026-08-30.
Other skills, from other repositories
comfyui-skill-openclaw
Run registered ComfyUI workflows through the fast comfyui-skill CLI, and use the official local Comfy MCP for live template, node, model, validation, and orchestration capabilities. Use this Skill when: (1) The user requests to "generate an image", "draw a picture", or "execute a ComfyUI workflow". (2) The user has…
business-skill-factory
A factory for turning a survey, standard operating procedure, workflow, or method into an installable AI skill. It gathers requirements, creates the skill files and tests, checks them, and can package the result.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
add-resend
Add Resend (email) channel integration via Chat SDK.
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.