Waku Agent is a local-first personal AI assistant whose readable code implements the agent loop, memory, and evaluation system. It is for people who want an assistant they can run and understand on their own laptop, with memory stored in SQLite and built-in testing. The catalogue add-ons support its agent workflow.
Borrowing it
Nothing to install: this file belongs to ShenSeanChen/waku-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ShenSeanChen/waku-agent/main/CLAUDE.mdgit clone --depth 1 https://github.com/ShenSeanChen/waku-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/shenseanchen/waku-agent/claude-md)<a href="https://agentmods.dev/instructions/shenseanchen/waku-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/shenseanchen/waku-agent/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/shenseanchen/waku-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/shenseanchen/waku-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.02548 | $0.02548 |
| Opus 5 | $0.01274 | $0.01274 |
| Sonnet 5 | $0.00510 | $0.00510 |
| Haiku 4.5 | $0.00255 | $0.00255 |
Grade A, and why
waku-agent 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 10d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
waku-agent — working conventions
Waku — a local-first personal assistant demonstrating the four pillars behind every serious agent: Harness, Loop, Memory, and Eval/LLM-Ops. It began as a teaching repo you could read in an afternoon, and it's now growing toward a full open-source assistant (the next Hermes / OpenClaw). The bar for every change: clear, honest code a newcomer can follow — each pillar legible on its own. The project will get bigger; it must never get muddier. New scope is welcome when it stays self-contained, tested, and readable; complexity for its own sake is not.
Architecture map (file ↔ diagram box)
waku/gateway/— cli, voice (wake word), telegram. Gateways only move text.waku/runtime/session.py— working memory assembly (SOUL.md + memory + history)waku/loop/agent.py— THE loop;loop/models.py— pluggable providers, 2 wire formatswaku/graph/— engine + node factories +workflows/(triage) — opt-in structure AROUND the loop (the loop never changes; a graph node can BE a loop turn); every failure fails open to the plain loopwaku/tools/— create_event / save_note / send_message (flagship task only)waku/memory/— semantic (FTS5) / episodic / procedural (SKILL.md) +retrieval_gate.py(hero 1) +consolidation.py(every N exchanges)waku/ops/— tracing (JSONL + OTel), dashboard (localhost:7777), release_gate,compare_history.py(the Compare arena's own JSONL scoreboard — never state.db)evals/deterministic/(0/1, pytest) vsevals/judge/(DeepEval, scored) — never mixexamples/— teaching material, not product (see the rule below); one folder per topic- Runtime state lives in
.waku/(state.db, calendar.ics, outbox/, traces/) — gitignored
Rules
- Be concise. Sean wants short replies: lead with the answer, cut preamble and recap. A few lines beats a wall of text. Expand only when he asks for detail.
- Start every session by draining the community queue. This is a public repo with contributors waiting; an unanswered PR teaches someone that doing what we asked gets silence. So on the first substantive turn of a new session, before anything else, run:
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.
- 10d ago First seen · 145 lines · 2,548 tokens per session scan A f34fb7eb7c32
waku-agent CLAUDE.md is an instructions file published in the GitHub repository ShenSeanChen/waku-agent (1,704 stars, last pushed 11d ago), licensed MIT. It adds 2,548 tokens to every session, about $0.0127 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.