Borrowing it
Nothing to install: this file belongs to j4flmao/agent-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/j4flmao/agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/j4flmao/agent-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/j4flmao/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/j4flmao/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/j4flmao/agent-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/j4flmao/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/j4flmao/agent-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 | $0.01594 | $0.01594 |
| Opus 5.5 | $0.00638 | $0.00638 |
| Sonnet 5.5 | $0.00319 | $0.00319 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
agent-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 26d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Reliability Rules
These rules govern every agent working in this repository. They are operational requirements, not suggestions.
1. Authority and execution
- Execute a clear, in-scope request immediately. Do not ask for confirmation, restate an approved plan, or say that you are ready to begin.
- Ask a question only when a missing fact cannot be safely inferred and proceeding could materially change the result, destroy data, expose a secret, or affect an external system.
- Once the user says to execute an agreed plan, execute it. Do not produce another plan unless the scope has changed or a blocker requires a new decision.
- Read the relevant skill, rule, and repository convention once, then apply it. Do not repeat the document back to the user.
- Keep work persistent until the request is complete, safely blocked, or requires user input. Never stop at a partial implementation and call it complete.
- When a method fails, change the diagnosis or method. Do not repeat the same failed action more than once without new evidence.
2. Truthfulness and verification
- Never claim that a task is complete, tested, deployed, reviewed, or successful unless the corresponding action actually happened.
- Report the exact verification performed and its result. If a command was not run, say so. If it failed, report the failure and do not present the work as passing.
- Never change tests merely to make them pass. Change tests only when the intended behavior or contract has changed, and explain why.
- Treat uncertain APIs, package names, CLI flags, versions, file paths, and configuration keys as unverified. Inspect the repository or authoritative documentation before using them.
- Prefer existing dependencies, utilities, patterns, and conventions in the repository. Do not invent a library, API, flag, or abstraction.
- Distinguish facts, observations, assumptions, and proposals. Label assumptions explicitly when they affect implementation.
- Do not agree with an incorrect premise merely to be agreeable. State the conflict, show the evidence, and propose the smallest correction.
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.
- 26d ago First seen · 113 lines · 1,594 tokens per session scan A 54f9549702db
agent-skills AGENTS.md is an instructions file published in the GitHub repository j4flmao/agent-skills (38 stars, last pushed 3d ago), licensed MIT. It adds 1,594 tokens to every session, about $0.0064 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 2026-10-11.
agent-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-skills AGENTS.mdj4flmao/agent-skills | Instructions file | 38 | 3d ago | MIT | A | 1,594 | 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 | today | 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 |