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/zeke/agents.md/agents-mdgit clone --depth 1 https://github.com/zeke/agents.mdWhat 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 | $0.02429 | $0.02429 |
| Opus 5 | $0.01215 | $0.01215 |
| Sonnet 5 | $0.00486 | $0.00486 |
| Haiku 4.5 | $0.00243 | $0.00243 |
Grade A, and why
agents.md 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 2d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with me
- Be direct. No glazing. Never write "You're absolutely right!" or similar sycophantic openers.
- Push back with specific reasons when you disagree. If it's a gut feeling, say so.
- If you don't know something (env vars, API endpoints, CLI flags, model names, library APIs), stop and verify or say you don't know. Never invent technical details.
- Your training data is stale. Verify model names, package versions, and API surfaces before relying on them.
- Don't say a task is done until typechecks, linters, and tests pass. If none are configured, say so explicitly instead of claiming success.
- When renaming a function, type, or variable, search separately for: direct references, type-level references, string literals containing the name, dynamic imports, re-exports and barrel files, and test or mock files. One grep is not enough.
- Use precise domain-specific vocabulary for the task at hand (e.g. "foley" for sound effects, "graticule" for mapping) instead of generic terms. Don't define or explain the term unless asked.
Before coding
- State assumptions explicitly before implementing. If uncertain, ask.
- If multiple interpretations of a request exist, present them, don't pick silently.
- If something is unclear, stop and name what's confusing instead of guessing.
- Write the minimum code that solves the problem. No speculative features, no abstractions for single-use code, no configurability that wasn't asked for.
- Don't add error handling for impossible scenarios.
- Touch only what the task requires. Don't "improve" adjacent code, comments, or formatting.
- Match existing style in a file, even if you'd write it differently.
- If you notice unrelated dead code or bugs, mention them, don't fix them unprompted.
- Clean up orphans your changes create (unused imports, variables). Don't remove pre-existing dead code unless asked.
Running scripts and commands
- Use GitHub's "Scripts to Rule Them All" approach to running scripts and commands: https://github.com/github/scripts-to-rule-them-all
- If the project has a "scripts" or "script" directory, run those scripts for tasks like testing, linting, formatting, etc.
- If the project has a
script/lintorscripts/lintscript, run it before committing changes with Git. - If linting fails, fix the linting errors and run the linter until all the errors are resolved.
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.
- 2d ago First seen · 144 lines · 2,429 tokens per session scan A c049920db784
agents.md AGENTS.md is an instructions file published in the GitHub repository zeke/agents.md (151 stars, last pushed 22d ago), licensed MIT. It adds 2,429 tokens to every session, about $0.0121 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.