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/leemysw/agent-kit/agents-mdgit clone --depth 1 https://github.com/leemysw/agent-kitWhat 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 | $0.00578 | $0.00578 |
| Opus 5 | $0.00289 | $0.00289 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
agent-kit 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
agent/ contains the FastAPI backend, WebSocket flow, session management, and persistence (service/, api/, shared/, utils/).
web/ is the Next.js frontend (src/components, src/hooks, src/lib, src/store).
alembic/ stores database migrations; keep schema changes and migration files in the same PR.
tests/ currently holds integration-style scripts and runtime logs (for example, interrupt/session behavior).
docs/ includes architecture and feature guides; update docs when behavior or API contracts change.
Build, Test, and Development Commands
make install: install backend (agent/requirements.txt) and frontend dependencies.make dev: run backend (python main.py) and frontend (cd web && npm run dev) together.make run-backend/make run-web: run one side only.alembic upgrade head: apply latest DB migrations.cd web && npm run build: production frontend build.cd web && npm run lint: frontend lint check.python -m py_compile agent/...: fast backend syntax smoke check.cd web && npx tsc --noEmit: TypeScript type check.
Coding Style & Naming Conventions
Python: follow Google Python style, object-oriented design, and use Chinese comments for non-trivial logic. Use snake_case for functions/files and PascalCase for classes.
TypeScript/React: components in PascalCase, hooks in useXxx style, and keep message/session types centralized under web/src/types.
Prefer small, composable handlers/processors over monolithic functions.
Testing Guidelines
This repository mainly uses integration-style validation instead of heavy unit coverage.
Primary checks before PR:
- backend compile smoke check (
py_compile); - frontend type/lint checks (
tsc,eslint); - targeted manual flow test for chat/interrupt/session history.
Add new tests undertests/withtest_<feature>.pynaming.
Commit & Pull Request Guidelines
History favors emoji-prefixed Conventional-style subjects (for example, :sparkles:, :bug:, :recycle:, :memo:) with concise Chinese summaries.
PRs should include:
- problem statement and scope;
- key file/path changes;
- commands run for validation;
- screenshots for UI changes and sample logs for message/session pipeline updates;
- migration/environment notes when applicable.
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 · 44 lines · 578 tokens per session scan A a67572d4da08
agent-kit AGENTS.md is an instructions file published in the GitHub repository leemysw/agent-kit (53 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 578 tokens to every session, about $0.0029 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
claude-proj-blueprint CLAUDE.md
Claude Code instructions for maduwanthasathsara0-hub/claude-proj-blueprint, covering project, tech stack, architecture, documentation directories and code conventions.
modeldriveprotocol AGENTS.md
Instructions for modeldriveprotocol/modeldriveprotocol, covering agents.md, purpose, read routes and routing rules.
claude-agent-server CLAUDE.md
Use Bun instead of Node.js, npm, pnpm, or vite.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.