Borrowing it
Nothing to install: this file belongs to lfglabs-dev/awesome-amp-code. 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/lfglabs-dev/awesome-amp-code/main/AGENTS.mdgit clone --depth 1 https://github.com/lfglabs-dev/awesome-amp-codeWrote 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/lfglabs-dev/awesome-amp-code/agents-md)<a href="https://agentmods.dev/instructions/lfglabs-dev/awesome-amp-code/agents-md"><img src="https://agentmods.dev/badge/instructions/lfglabs-dev/awesome-amp-code/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/lfglabs-dev/awesome-amp-code/agents-md"><img src="https://agentmods.dev/badge/instructions/lfglabs-dev/awesome-amp-code/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 | $0.00385 | $0.00385 |
| Opus 5.5 | $0.00154 | $0.00154 |
| Sonnet 5.5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
awesome-amp-code 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 Guidelines for awesome-amp-cli Repository
Build, Lint & Test Commands
- Lint readme:
npx awesome-lint readme.md - Link check:
awesome_bot --allow-redirect --white-list https://github.com/lfglabs-dev/awesome-amp-code,https://example.com readme.md - Node.js version: Use v21.6.0 (as specified in .tool-versions)
Code Style Guidelines
- Markdown Format: Follow standard Markdown formatting for documentation
- List Items: Add items at the bottom of existing lists
- Item Format:
- [item name](https link) - Description beginning with capital, ending in period. - Commits: Always create a new branch for proposed changes
- PR Process: Check spelling and grammar before submitting
- Code of Conduct: All contributions must adhere to the Code of Conduct
Project Structure
- Documentation is the primary focus of this repository
- Main content is in amp_cli_docs.md and readme.md
- CI pipeline uses awesome-lint and awesome_bot to validate content
Add link to Projects & Tools section
When /builtwith followed by a link is included in a prompt, you will add the link to the "Projects & Tools" section of the README.md file under the appropriate subcategory (Documentation & Guides, Development Tools, Applications Built with Amp, or Browser & Misc). If there is a numbered list of urls, create subagents to complete the tasks.
Add link to @docs/amp_faq.md
When /faq followed by a link is included in a prompt, you will add the link to the @docs/amp_faq.md file in between --- and --- Place it above the last question. The update the Last Modified date
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 · 31 lines · 385 tokens per session scan A 93f73aeb0947
awesome-amp-code AGENTS.md is an instructions file published in the GitHub repository lfglabs-dev/awesome-amp-code (79 stars, last pushed 9mo ago), licensed CC0-1.0. It adds 385 tokens to every session, about $0.0015 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.
awesome-amp-code AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| awesome-amp-code AGENTS.mdlfglabs-dev/awesome-amp-code | Instructions file | 79 | 9mo ago | CC0-1.0 | A | 385 | Codex, OpenCode |
| awesome-ai-conventions copilot-instructions.mdGuilhermeAlbert/awesome-ai-conventions | Instructions file | 39 | 1mo ago | none | A | 85 | GitHub Copilot |
| awesome-ai-rules copilot-instructions.mdshumatsumonobu/awesome-ai-rules | Instructions file | 1 | 3mo ago | MIT | A | 236 | GitHub Copilot |
| 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 | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |