Borrowing it
Nothing to install: this file belongs to microwind/ai-prompt. 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/microwind/ai-prompt/main/AGENTS.mdgit clone --depth 1 https://github.com/microwind/ai-promptWrote 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/microwind/ai-prompt/agents-md)<a href="https://agentmods.dev/instructions/microwind/ai-prompt/agents-md"><img src="https://agentmods.dev/badge/instructions/microwind/ai-prompt/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/microwind/ai-prompt/agents-md"><img src="https://agentmods.dev/badge/instructions/microwind/ai-prompt/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 | $0.00658 | $0.00658 |
| Opus 5.5 | $0.00263 | $0.00263 |
| Sonnet 5.5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
ai-prompt 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
- Core guides live in
README.md,README_EN.md,docs/articles/programmer_prompt_engineering_guide.md, anddocs/articles/developer_prompt_engineering_guide.md. - Fourteen task playbooks sit in
01-Requirement-Clarification…14-Documentation-Generation, each with aREADME.md(and occasional checklists/examples). Keep new task folders numbered with two digits and kebab-case names. - Scenario libraries:
Prompt-Examples/holds domain examples (content, system design, data, code);Prompt-Frameworks/stores framework cheat-sheets (CRISPE, RTF, etc.). - Quick navigation lives in
QUICK-REFERENCE.mdand项目完整导航.md; archive stale material under_ARCHIVE/rather than deleting.
Build, Test, and Development Commands
- No build toolchain is required; the repo is Markdown-first.
- Recommended checks before pushing:
git statusto confirm only intended files change.rg "TODO|🔄"to catch unfinished placeholders.- Optional:
npx markdownlint "**/*.md"if you have markdownlint globally; align with default rules (no custom config yet).
Coding Style & Naming Conventions
- Write in concise Markdown; start each file with a single
#title that matches the page purpose (bilingual titles are welcome, e.g.,T01: Requirement Clarification（需求澄清）). - Prefer short paragraphs, ordered lists for steps, and tables/checklists for prompts. Use fenced code blocks with language tags for prompts or command samples.
- File/dir names: lowercase kebab-case; keep numeric prefixes for task folders and sequential examples (e.g.,
01-Content-Generation/01-Entertainment/03-tv-series-summary.md). - Emojis ✅/🔄 are used to signal status in catalogs; keep that convention when adding new entries.
Testing Guidelines
- There is no automated test suite; perform manual checks: preview Markdown, verify internal links, and ensure code blocks or prompts render correctly in common viewers (GitHub, mdbook style).
- For new prompts, run them once against your target model to confirm the instruction flow and expected outputs; capture a minimal example if helpful.
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 · 34 lines · 658 tokens per session scan A 1a675d782b1e
ai-prompt AGENTS.md is an instructions file published in the GitHub repository microwind/ai-prompt (61 stars, last pushed 6mo ago), licensed MIT. It adds 658 tokens to every session, about $0.0026 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.
ai-prompt AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-prompt AGENTS.mdmicrowind/ai-prompt | Instructions file | 61 | 6mo ago | MIT | A | 658 | 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 |