Borrowing it
Nothing to install: this file belongs to ashermahonin/agentic-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ashermahonin/agentic-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/ashermahonin/agentic-skillsWrote 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/ashermahonin/agentic-skills/agents-md)<a href="https://agentmods.dev/instructions/ashermahonin/agentic-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ashermahonin/agentic-skills/agents-md/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/instructions/ashermahonin/agentic-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ashermahonin/agentic-skills/agents-md.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 | $0.00914 | $0.00914 |
| Opus 5.5 | $0.00366 | $0.00366 |
| Sonnet 5.5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
agentic-skills 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 2mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Skills repository rules
Purpose
This repository maintains 47 portable Agent Skills, their route map, client adapters, project-memory skeleton, documentation, installer, and validator.
Repository map
- agentic/skills: self-contained skills in the open Agent Skills format.
- agentic/routing/skills.json: entrypoints, order, permissions, and combinations.
- agentic/standards: runtime capability contract.
- agentic/compatibility: verified client map.
- agentic/adapters: client-specific integration without provider logic in core skills.
- agentic/docs: English, Russian, Spanish, and Chinese documentation.
- agentic/obsidian: linked project-memory templates.
- agentic/scripts: repository validation and deterministic documentation generators.
- install.sh: global and project-local installation.
Working rules
- Select the smallest route that owns the task. Do not run broad discovery for a bounded, familiar change.
- Check the runtime capabilities required by the route. Missing tools change the deliverable; they do not justify invented evidence.
- Preserve user scope, permissions, dirty files, and existing project instructions.
- Use current primary documentation when external technology or standards affect a decision. Prefer Context7 MCP when available.
- Keep temporary scripts, screenshots, logs, and generated output out of the repository root.
- Use a failing test before production code when an automated test can provide useful regression evidence. Record another verification method when it cannot.
- Apply engineering-quality to production code and focused refactors.
- Keep production writes inside service-implementation ownership; review skills remain read-only unless fixes are requested.
- Match validation and security depth to the affected surface and blast radius.
- Update the canonical documentation and project memory when behaviour, operation, architecture, or durable decisions change.
- Apply agentic/routing/principal-operating-model.md before critical writes.
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.
- 2mo ago First seen · 83 lines · 914 tokens per session scan A 958c3c19204c
agentic-skills AGENTS.md is an instructions file published in the GitHub repository ashermahonin/agentic-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 914 tokens to every session, about $0.0037 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.
agentic-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentic-skills AGENTS.mdashermahonin/agentic-skills | Instructions file | 10 | 2mo ago | MIT | A | 914 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |