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/lilithgames/a2wave/agents-mdgit clone --depth 1 https://github.com/LilithGames/a2waveWhat 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 | $0.01499 | $0.01499 |
| Opus 5 | $0.00749 | $0.00749 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
a2wave 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
a2wave — Project Guide
Natural-language-driven Agent orchestration: a general-purpose Agent building and orchestration platform for enterprises, published over API / Feishu / Slack / Discord / A2A / scheduled / chat page / GitLab & GitHub repository triggers.
Primary language: English. This is an OSS-facing repository — all code, comments, commit messages, documentation, and identifiers must be written in English.
Trust model: Agent authors and users are trusted colleagues; controls enforce accountability and least privilege, not containment of a hostile insider — never harden against a malicious authenticated author, and never skip auth, anonymous-invoke, drop an audit entry, or put credentials in details. Full statement: trust model & Iron Rules · SECURITY.md.
Architecture
a2wave (pnpm monorepo)
├── apps/api/ # Hono + SQLite (Drizzle ORM) + Local Agent Execution
├── apps/web/ # React 19 + Vite + TailwindCSS v4 + Ant Design
├── apps/cli/ # CLI tool (a2wave command)
└── packages/shared/ # Zod schemas & types
Stack: TypeScript, Biome (lint), TanStack Query, React Router v7, Vitest + Playwright.
Product boundary
Six Iron Rules define what a2wave will and will not build — check every new feature against them first: docs/agent/iron-rules.md. Violations need maintainer sign-off before proceeding.
Commands
pnpm install # install
cp .env.example .env # leave AUTH_SECRET empty — pnpm dev generates one
pnpm run dev # API :3502 + Web :3501 (override with PORT / WEB_PORT)
pnpm stop # free the ports if a previous run left orphans
pnpm test # all unit/integration tests
pnpm db:migrate # run migrations for the DATABASE_URL backend
Setup detail, database backends, worktree conventions: docs/agent/development.md.
Gates — non-negotiable, --no-verify forbidden
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 · 81 lines · 1,499 tokens per session scan A 90c791fa92f2
a2wave AGENTS.md is an instructions file published in the GitHub repository LilithGames/a2wave (24 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,499 tokens to every session, about $0.0075 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
herdr AGENTS.md
AGENTS.md instructions for herdrdev/herdr, covering herdr, scope and audience, universal project rules, principles and multiplicative performance paths.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
kungfu CLAUDE.md
Claude Code instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before working in this repository. It routes both product use and contribution work to the repository sources of truth, including the requirement that development and build tasks enter through Shifu.
cyrus copilot-instructions.md
Copilot instructions for cyrusagents/cyrus: Note, there is a need to maintain the use of '--print' when running the claude exec commands because that is what makes it non-interactive.
agent-skills GEMINI.md
Instructions for mongodb/agent-skills, covering mongodb gemini extension and configuration.
cyrus CLAUDE.md
Claude Code instructions for cyrusagents/cyrus, covering claude.md, project overview, how cyrus works, example interaction and test drives.