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/extra-org/extra/claude-mdgit clone --depth 1 https://github.com/extra-org/extraWhat 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 | $0.00287 | $0.00287 |
| Opus 5 | $0.00143 | $0.00143 |
| Sonnet 5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
extra 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 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.
What it actually says
CLAUDE.md
Declarative platform for building AI agent systems. See docs/ for architecture details and tasks/ for current work.
Naming
The product/brand name is Extra (matches the GitHub repo, docs site, and docs.json). agent-engine is only the PyPI/package name of the core engine; agentctl and agent-manager are the CLI/console scripts. Don't call the product "Agent Engine" in user-facing copy (README, docs landing page) — use "Extra".
Skills
Skills, roles, and workflows live in .ai/ — the single source of truth. .claude/skills/ is generated from there (make generate-ai). Do not edit generated files directly.
Commands
make generate-ai # regenerate .claude/, .codex/ from .ai/
make format # ruff format
make lint # ruff check
make typecheck # mypy
make test # pytest
make check # format-check + lint + typecheck + test + generated-stub check
Guardrails
- Do not skip tests or hardcode secrets.
- Do not change architecture decisions without explicit approval.
- Do not edit
.claude/skills/,.claude/agents/, or.claude/workflows/directly.
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 · 29 lines · 287 tokens per session scan A 01d5c1fa90f3
extra CLAUDE.md is an instructions file published in the GitHub repository extra-org/extra (108 stars, last pushed 4d ago), licensed MIT. It adds 287 tokens to every session, about $0.0014 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
framework AGENTS.md
Instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
platform CLAUDE.md
Instructions for ambient-code/platform, covering ambient code platform, structure, key files, session flow and commands.
autogen copilot-instructions.md
Copilot instructions for microsoft/autogen, covering autogen multi-agent ai framework, working effectively, prerequisites and environment setup, python development workflow and quick validation (under 1 second each).
toh-framework CLAUDE.md
Instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
jentic-one GEMINI.md
Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).