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/cyzlmh/agentype/agents-mdgit clone --depth 1 https://github.com/cyzlmh/agentypeWrote 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/cyzlmh/agentype/agents-md)<a href="https://agentmods.dev/instructions/cyzlmh/agentype/agents-md"><img src="https://agentmods.dev/badge/instructions/cyzlmh/agentype/agents-md.svg" alt="Measured on agentmods" 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 | $0.00680 | $0.00680 |
| Opus 5 | $0.00340 | $0.00340 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
agentype 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 4d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Agentype is a Python CLI package under src/agentype/. The command entry point is src/agentype/__init__.py, wired through pyproject.toml as agentype = "agentype:main". Data collection lives in collector.py; per-agent adapters live in src/agentype/sources/ for Claude Code, Codex, OpenCode, pi-agent, Gemini CLI, OpenClaw, Nanobot, and configured Nanobot-compatible roots. Statistics, domain scoring, and archetype selection live in analysis.py.
Project documentation is in README.md, SKILL.md, and RELEASE.md. ROADMAP.md is a local planning file and is intentionally ignored. Tests are in tests/. Runtime artifacts are written to output/ and are intentionally ignored.
Build, Test, and Development Commands
Use uv for dependency management and command execution.
uv syncinstalls dependencies fromuv.lock.uv run pytestruns the parser and token usage test suite.uv run agentypeprints the end-user usage overview and archetype.uv run agentype -vadds intermediate statistics, domain evidence, and data confidence tables.uv run agentype --json-outwrites the full analysis tooutput/agentype.json.uv buildbuilds the package usinguv_build.
If you add developer tools such as ruff or mypy, declare them in pyproject.toml and run them through uv run.
Coding Style & Naming Conventions
Write idiomatic Python 3.12 with 4-space indentation and type hints for public functions or non-obvious data shapes. Use snake_case for functions, variables, and modules; use PascalCase for dataclasses such as SkillInfo, SessionEvent, and TokenUsage.
Keep modules focused on their existing responsibilities. Prefer small functions over new abstractions unless the abstraction removes repeated logic. Match the current style: standard-library imports first, third-party imports next, then local imports.
Testing Guidelines
Use pytest and place test files under tests/ with names like test_sources.py, test_token_usage.py, or test_analysis.py. Prefer fixture files or small inline JSON/SQLite samples over reading real local agent history. Focus on deterministic logic: transcript parsing, token usage summarization, statistics, domain scoring, and archetype selection. Avoid tests that require live LLM calls; mock agentype.llm.chat instead.
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.
- 4d ago First seen · 47 lines · 680 tokens per session scan A ba298012e6c2
agentype AGENTS.md is an instructions file published in the GitHub repository cyzlmh/agentype (2 stars, last pushed 4mo ago), licensed MIT. It adds 680 tokens to every session, about $0.0034 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
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).
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.
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.