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/apolenkov/feynman/agents-mdgit clone --depth 1 https://github.com/apolenkov/feynmanWhat 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 | $0.00385 | $0.00385 |
| Opus 5 | $0.00192 | $0.00192 |
| Sonnet 5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
feynman 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.
What it actually says
AGENTS.md
Universal agent rules for feynman — the single entry point. All AI tools
(Claude Code, Codex, …) read this file. CLAUDE.md is just @AGENTS.md.
Thin by design. Engineering standards are enforced by tooling and documented in the canonical files below — never duplicated here. If a fact lives in two places, one of them is wrong.
Before committing
Run npm run typecheck, npm run eslint, and npm test — all green.
Two linters — don't confuse them
npm run lint→ feynman's product diagram linter (bin/feynman-lint, rules L01–L15)npm run eslint→ the code linter (eslint .)
Canonical sources — each fact has exactly one home
| Topic | Home |
|---|---|
| Domain language (Structure, Trigger, Visual, Intensity) — use exactly, no synonyms | CONTEXT.md |
| Architecture (hook lifecycle, lint pipeline, state schema) | docs/architecture.md |
| Decisions & constraints (toolchain, zero-runtime-deps, Node baseline) | docs/adr/ (start at 0001) |
| Agent ops (issue tracker, triage labels, domain workflow) | docs/agents/ |
| Planning / specs | openspec/ |
Targets
Claude Code, Codex, and OpenCode are the three first-class install targets
(--target all expands to exactly these). IDE adapters (Cline, Cursor,
Windsurf) are not supported.
Commits
Conventional Commits (type: subject, imperative).
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 · 38 lines · 385 tokens per session scan A ed3a6aafd1c4
feynman AGENTS.md is an instructions file published in the GitHub repository apolenkov/feynman (1 stars, last pushed 16d ago), licensed MIT. It adds 385 tokens to every session, about $0.0019 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
autotask-mcp dev_workflow.instructions.md
Guide for using Taskmaster to manage task-driven development workflows.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
foggy-data-mcp-bridge-python CLAUDE.md
Instructions for foggy-projects/foggy-data-mcp-bridge-python, covering foggy data mcp bridge — python, 快速启动, 安装依赖, 运行测试 and 启动 mcp 服务（连接 docker mysql）.
McpServer AGENTS.md
AGENTS.md instructions for sharpninja/McpServer, covering agent instructions, session start, rules, byrd test gate and where things live.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.