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 agentmods add instructions/thuanvd378/write-me-a-readme/agents-mdgit clone --depth 1 https://github.com/thuanvd378/write-me-a-readmeWrote 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/instructions/thuanvd378/write-me-a-readme/agents-md)<a href="https://agentmods.dev/instructions/thuanvd378/write-me-a-readme/agents-md"><img src="https://agentmods.dev/badge/instructions/thuanvd378/write-me-a-readme/agents-md.svg" alt="Measured on agentmods" 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 | $0.00445 | $0.00445 |
| Opus 5 | $0.00222 | $0.00222 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
write-me-a-readme AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guidance
Source of truth
- The canonical skill is
plugins/write-a-readme/skills/readme/. - Keep the skill name
readmeand its folder name identical. - Treat files under
adapters/andplugins/write-a-readme/commands/as thin invocation adapters; do not duplicate the full workflow there. - Keep Codex plugin metadata in
plugins/write-a-readme/.codex-plugin/plugin.jsonaligned withSKILL.mdandagents/openai.yaml. - Keep Claude plugin metadata in
plugins/write-a-readme/.claude-plugin/plugin.json; the repository-root.claude-plugin/marketplace.jsononly catalogs it.
Content rules
- Derive README guidance from repository evidence and cited first-party sources.
- Do not copy README prose, banners, screenshots, icons, or brand assets from example repositories.
- Do not claim that any output guarantees SEO rank, GitHub Trending placement, stars, or adoption.
- Record a source page, author, license, restrictions, retrieval date, and modifications for every downloaded visual.
- Keep core
SKILL.mdconcise. Put detailed, conditionally loaded guidance one level down inreferences/.
Implementation rules
- Support Python 3.10 or newer.
- Keep project inspection and README validation standard-library-only.
- Keep banner rendering limited to Pillow plus the standard library.
- Keep unit tests offline and deterministic; mock network responses.
- Reject path traversal, active SVG content, remote final assets, secret-bearing files, and silent overwrite by default.
Verification
Run from the repository root:
python -m pip install -r plugins/write-a-readme/skills/readme/requirements.txt
python -m unittest discover -s tests -v
python C:/Users/ADMIN/.codex/skills/.system/skill-creator/scripts/quick_validate.py plugins/write-a-readme/skills/readme
python C:/Users/ADMIN/.codex/skills/.system/plugin-creator/scripts/validate_plugin.py plugins/write-a-readme
The last two paths are local Codex development helpers and are not assumed to exist in public CI.
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.
- 5d ago First seen · 39 lines · 445 tokens per session scan A 6ab4025d97d7
write-me-a-readme AGENTS.md is an instructions file published in the GitHub repository thuanvd378/write-me-a-readme (1 stars, last pushed 1mo ago), licensed MIT. It adds 445 tokens to every session, about $0.0022 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.
Other instructions, from other repositories
agent-stylebooks AGENTS.md
Instructions for Neeeophytee/agent-stylebooks, a project described as: 11 installable editorial systems for AI agents, based on leading public style guides.
agent-stylebooks CLAUDE.md
Instructions for Neeeophytee/agent-stylebooks: Read and follow AGENTS.md. The same maintenance rules apply in Claude Code and other agent environments.
core copilot-instructions.md
Copilot instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
docs AGENTS.md
AGENTS.md instructions for argos-ci/docs, covering agents.md, always use the documentation skills and keep the table of contents in sync.
everything-gemini-code GEMINI.md
Gemini CLI instructions for Jamkris/everything-gemini-code, covering project instructions, prompt defense baseline and guidelines.
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.