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/tomzx/agents/agents-mdgit clone --depth 1 https://github.com/tomzx/agentsWhat 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 | $0.00748 | $0.00748 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
agents 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General
- Be concise
- Do not use em-dashes, use commas or parentheses instead
- One sentence per line
- Avoid using the following terms (unless it is the most appropriate): shape, honest, load bearing
- When a skill explicitly recommends running another skill as an upstream/prerequisite (for example create-article recommending research-article when sources are not yet gathered), and you choose not to follow that recommendation, you must say so and give your reasoning before proceeding, so it can be course-corrected. Surfacing the deviation after the fact is not sufficient.
Python
- Use uv for package management
- When creating a project, always use the most recent Python LTS version
- Use type hints
- Use pytest for testing
- Use ruff for linting/formatting
- Run tests before committing
- Run linter/formatter before committing
- Create "green path" tests that cover the main functionality
- Use structlog for logging
- When adding dependencies, use
uv add ...over adding the version directly to pyproject.toml - Keep init.py files minimal/empty, only for package initialization
- Do NOT use/add all in init.py files
Per-repository instructions
- Before working in a git repository, check for per-repository overrides stored outside that repository.
- Find the skills library root by resolving the real path of this AGENTS.md (follow symlinks), then look in its
repositories/directory, which is a sibling ofskills/. - Derive
{owner}/{repository}from the current repository's GitHub remote URL. - If
repositories/{owner}/{repository}/AGENTS.mdexists, read and apply it together with these base instructions. - For forks, symlink
repositories/{fork-owner}/{repository}to the upstreamrepositories/{owner}/{repository}so both resolve to the same instructions.
Per-machine instructions
- Some machines carry local overrides that should not be shared (e.g. employer-specific conventions).
- Find the skills library root by resolving the real path of this AGENTS.md (follow symlinks), then look in its
machines/directory, which is a sibling ofskills/. machines/*/profiles are gitignored and exist only on the current machine. Read and apply everymachines/*/AGENTS.mdthat is present, together with these base instructions.
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 · 42 lines · 748 tokens per session scan A 94c7b1cf700a
agents AGENTS.md is an instructions file published in the GitHub repository tomzx/agents (5 stars, last pushed 5d ago), licensed MIT. It adds 748 tokens to every session, about $0.0037 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 2026-08-31.
Other instructions, from other repositories
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.
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).
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.
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).
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.
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.