Borrowing it
Nothing to install: this file belongs to ChaoYue0307/awesome-loop-engineering. 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/ChaoYue0307/awesome-loop-engineering/main/AGENTS.mdgit clone --depth 1 https://github.com/ChaoYue0307/awesome-loop-engineeringWrote 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/chaoyue0307/awesome-loop-engineering/agents-md)<a href="https://agentmods.dev/instructions/chaoyue0307/awesome-loop-engineering/agents-md"><img src="https://agentmods.dev/badge/instructions/chaoyue0307/awesome-loop-engineering/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/chaoyue0307/awesome-loop-engineering/agents-md"><img src="https://agentmods.dev/badge/instructions/chaoyue0307/awesome-loop-engineering/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 | $0.00611 | $0.00611 |
| Opus 5.5 | $0.00244 | $0.00244 |
| Sonnet 5.5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
awesome-loop-engineering 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidance For AI Agents
This repository curates resources for the new AI/coding-agent meaning of Loop Engineering.
Scope
Include resources that help readers design, run, verify, evaluate, or critique recurring AI-agent systems that sit above prompt, context, and harness engineering. A good entry should explain how a loop discovers work, delegates to agents, supplies context, bounds tools and permissions, verifies results, persists state, decides next actions, retries, or escalates.
Do not include unrelated uses of "loop":
- software event loops;
- UI/game loops;
- control theory;
- growth loops;
- generic workflow automation;
- non-AI feedback loops.
Editing Rules
- Keep
README.mdas the canonical English source. - Preserve the four-layer framing when editing the intro, scope, or mental model: prompt, context, and harness engineering improve one run; Loop Engineering governs repeated agent work over time.
- Keep annotations short, specific, and builder-oriented.
- Prefer primary sources, official docs, papers, and implementation-heavy write-ups.
- If a resource is generic agent, prompt, context, or harness content, include it only when the annotation clearly explains its loop-design relevance.
- Update
README.zh-CN.mdonly for translated overview content; do not let it drift into a separate resource list unless maintained. - When adding a new category, update
README.md,CONTRIBUTING.md, PR templates, and issue templates together. - Do not add generated marketing copy or unsupported hype.
Commit Identity Rule
Never create commits with AI-assistant co-author trailers or any non-owner author/committer identity. All commits in this repository must be authored and committed as ChaoYue0307 <[email protected]>.
When committing from an AI agent, do not use plain git commit if the environment may append co-author trailers. Create commits with explicit identity instead:
git add <files>
PARENT="$(git rev-parse HEAD)"
TREE="$(git write-tree)"
NEW="$(GIT_AUTHOR_NAME='ChaoYue0307' GIT_AUTHOR_EMAIL='[email protected]' GIT_COMMITTER_NAME='ChaoYue0307' GIT_COMMITTER_EMAIL='[email protected]' git commit-tree "$TREE" -p "$PARENT" -m "Commit message")"
git update-ref refs/heads/main "$NEW" "$PARENT"
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 · 63 lines · 611 tokens per session scan A 274d416b5a52
awesome-loop-engineering AGENTS.md is an instructions file published in the GitHub repository ChaoYue0307/awesome-loop-engineering (59 stars, last pushed 3d ago), licensed CC0-1.0. It adds 611 tokens to every session, about $0.0024 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-loop-engineering AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| awesome-loop-engineering AGENTS.mdChaoYue0307/awesome-loop-engineering | Instructions file | 59 | 3d ago | CC0-1.0 | A | 611 | Codex, OpenCode |
| agent-rulescope tests.instructions.md13624725933/agent-rulescope | Instructions file | 1 | 3mo ago | MIT | A | 38 | GitHub Copilot |
| 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 |