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/567-labs/instructor/claude-mdgit clone --depth 1 https://github.com/567-labs/instructorWhat 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 | $0.03148 | $0.03148 |
| Opus 5 | $0.01574 | $0.01574 |
| Sonnet 5 | $0.00630 | $0.00630 |
| Haiku 4.5 | $0.00315 | $0.00315 |
Grade A, and why
instructor CLAUDE.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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Instructor Development Guide
Commands
- Install deps:
uv pip install -e ".[dev,anthropic]"orpoetry install --with dev,anthropic - Run tests:
uv run pytest tests/ -n auto - Run specific test:
uv run pytest tests/path_to_test.py::test_name - Skip LLM tests:
uv run pytest tests/ -k 'not llm and not openai' - Type check:
uv run ty check - Lint:
uv run ruff check instructor examples tests - Format:
uv run ruff format instructor examples tests - Generate coverage:
uv run coverage run -m pytest tests/ -k "not docs"thenuv run coverage report - Build documentation:
uv run mkdocs serve(for local preview) or./build_mkdocs.sh(for production) - Waiting: use
sleep <seconds>for explicit pauses (e.g., CI waits) or to let external processes finish
Installation & Setup
- Fork the repository and clone your fork
- Install UV:
pip install uv - Create virtual environment:
uv venv - Install dependencies:
uv pip install -e ".[dev]" - Install pre-commit:
uv run pre-commit install - Run tests to verify:
uv run pytest tests/ -k "not openai"
Code Style Guidelines
- Typing: Use strict typing with annotations for all functions and variables
- Imports: Standard lib → third-party → local imports
- Formatting: Follow Black's formatting conventions (enforced by Ruff)
- Models: Define structured outputs as Pydantic BaseModel subclasses
- Naming: snake_case for functions/variables, PascalCase for classes
- Error Handling: Use custom exceptions from exceptions.py, validate with Pydantic
- Comments: Docstrings for public functions, inline comments for complex logic
Conventional Commits
- Format:
type(scope): description - Types: feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert
- Examples:
feat(anthropic): add support for Claude 3.5fix(openai): correct response parsing for streamingdocs(README): update installation instructionstest(gemini): add validation tests for JSON mode
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 · 304 lines · 3,148 tokens per session scan A 374feaaccf38
instructor CLAUDE.md is an instructions file published in the GitHub repository 567-labs/instructor (13,803 stars, last pushed 3d ago), licensed MIT. It adds 3,148 tokens to every session, about $0.0157 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
openai-agents-python AGENTS.md
Instructions for openai/openai-agents-python, covering contributor guide, policies & mandatory rules, mandatory skill usage, work status reporting and git worktree and branch safety.
E2B CLAUDE.md
Instructions for e2b-dev/E2B: Use pnpm for node and uv for python to install and update dependencies. Run pnpm run format, pnpm run lint and pnpm run typecheck before committing changes. When modifying the SDK packages, ensure equivalent changes are applied to both JS as well as sync and async Python implementations.…
Patter AGENTS.md
Instructions for PatterAI/Patter, covering agents.md, non-negotiables (ci and reviewers block on these), before opening a pr, where things live and commits & prs.
AutoGPT copilot-instructions.md
Copilot instructions for Significant-Gravitas/AutoGPT, covering github copilot instructions for autogpt, repository overview, build and validation instructions, essential setup commands and runtime requirements.
AutoGPT AGENTS.md
AGENTS.md instructions for Significant-Gravitas/AutoGPT, covering autogpt platform contribution guide, directory overview, code style, frontend guidelines and testing.
dify AGENTS.md
AGENTS.md instructions for langgenius/dify, covering agents.md and repository gotchas.