Borrowing it
Nothing to install: this file belongs to minghinmatthewlam/agent-guards. 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/minghinmatthewlam/agent-guards/main/AGENTS.mdgit clone --depth 1 https://github.com/minghinmatthewlam/agent-guardsWrote 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/minghinmatthewlam/agent-guards/agents-md)<a href="https://agentmods.dev/instructions/minghinmatthewlam/agent-guards/agents-md"><img src="https://agentmods.dev/badge/instructions/minghinmatthewlam/agent-guards/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/minghinmatthewlam/agent-guards/agents-md"><img src="https://agentmods.dev/badge/instructions/minghinmatthewlam/agent-guards/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 | $0.00248 | $0.00248 |
| Opus 5.5 | $0.00099 | $0.00099 |
| Sonnet 5.5 | $0.00050 | $0.00050 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
agent-guards 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.
What it actually says
Agent Operating Guidelines
- Code is the source of truth. Read and trace the current implementation before relying on documentation or asking the user. Ask only when product intent cannot be learned from the code.
- Before implementation, define observable success and the exact verification path. Look for a repo-local
verify-*skill or existing verification command first. If no repeatable path exists, create the smallest useful one; usecreate-verification-skillfor a product surface. - Do not report completion until you exercise the affected user-facing surface and observe the expected result. If verification is blocked, state what you tried and what is missing.
- Agents copy nearby patterns and take shortcuts. Keep one obvious path, remove misleading alternatives, and enforce important rules with structure, types, static analysis, tests, or CI.
- After a material mistake, use
learn-from-mistake. Route repository weaknesses throughrepo-setupand verification weaknesses through the verification skills. - Work from clear success criteria and use the available tools. Do not require step-by-step instructions when the goal and constraints are clear.
- Report the result, proof, important decisions, blockers, and residual risk. Keep details in diffs, logs, and artifacts.
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 Changed · -25 lines · -227 tokens per session 0117729f9cdb
- 2mo ago First seen · 35 lines · 475 tokens per session scan A b87ccf9086e7
agent-guards AGENTS.md is an instructions file published in the GitHub repository minghinmatthewlam/agent-guards (46 stars, last pushed today), licensed MIT. It adds 248 tokens to every session, about $0.0010 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 2026-08-30.
agent-guards AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-guards AGENTS.mdminghinmatthewlam/agent-guards | Instructions file | 46 | today | MIT | A | 248 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |