Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/millionco/debug-agent/agents-mdgit clone --depth 1 https://github.com/millionco/debug-agentWhat 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 | $0.00541 | $0.00541 |
| Opus 5 | $0.00270 | $0.00270 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
debug-agent 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 yesterday.
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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General Rules
- MUST: Use @antfu/ni. Use
nito install,nr SCRIPT_NAMEto run.nunto uninstall. - MUST: Use TypeScript interfaces over types.
- MUST: Keep all types in the global scope.
- MUST: Use arrow functions over function declarations
- MUST: Default to NO comments. Only add a comment when the user explicitly asks, or when the "why" is truly non-obvious — browser quirks, platform bugs, performance tradeoffs, fragile internal patching, or counter-intuitive design decisions. Never add comments that restate what the code does or what a well-named function/variable already conveys. When in doubt, leave the comment out.
- Do not delete descriptive comments >3 lines without confirming with the user
- MUST: Use kebab-case for files
- MUST: Use descriptive names for variables (avoid shorthands, or 1-2 character names).
- Example: for .map(), you can use
innerXinstead ofx - Example: instead of
movedusedidPositionChange
- Example: for .map(), you can use
- MUST: Frequently re-evaluate and refactor variable names to be more accurate and descriptive.
- MUST: Do not type cast ("as") unless absolutely necessary
- MUST: Remove unused code and don't repeat yourself.
- MUST: Always search the codebase, think of many solutions, then implement the most elegant solution.
- MUST: Put all magic numbers in
constants.tsusingSCREAMING_SNAKE_CASEwith unit suffixes (_MS,_PX). - MUST: Put small, focused utility functions in
utils/with one utility per file. - MUST: Use Boolean over !!.
Testing
Run checks always before committing with:
pnpm check # runs lint + fmt
Development instructions
This is a pnpm monorepo with packages/ (libraries). No external services (databases, Docker, etc.) are required.
Build before test
pnpm build must complete before running the CLI. After modifying source files, always rebuild.
Key commands reference
See root package.json scripts. Quick reference:
- Install:
ni(orpnpm install) - Build:
nr build(orpnpm build) - Lint:
pnpm lint— vite-plus lint - Format:
pnpm fmt— vite-plus fmt - Check:
pnpm check— lint + fmt combined
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.
- yesterday First seen · 46 lines · 541 tokens per session scan A 0649525a8397
debug-agent AGENTS.md is an instructions file published in the GitHub repository millionco/debug-agent (302 stars, last pushed 3mo ago), licensed MIT. It adds 541 tokens to every session, about $0.0027 per session on Opus 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.
Other instructions, from other repositories
taste-skill copilot-instructions.md
Instructions for Leonxlnx/taste-skill, covering copilot instructions: taste standard and the "anti-slop" manifesto for copilot.
she-love-me AGENTS.md
Instructions for 863401402/she-love-me, covering agents.md, repository focus and codex guidance.
skill-based-architecture AGENTS.md
Instructions for WoJiSama/skill-based-architecture, covering agents.md, quick routing (survives context truncation), auto-triggers and red flags — stop.
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
she-love-me copilot-instructions.md
Instructions for 863401402/she-love-me: When the user asks to import or analyze WeChat/QQ chat history, read and follow .agents/skills/she-love-me/SKILL.md from the repository root.
she-love-me GEMINI.md
Instructions for 863401402/she-love-me: For WeChat or QQ chat import and relationship analysis, use .agents/skills/she-love-me/SKILL.md as the authoritative workflow. Read its referenced files when routed, especially references/data-sources.md for end-to-end exporter installation and operation.