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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/shenseanchen/waku-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/shenseanchen/waku-agent/agents-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/agents-md"><img src="https://agentmods.dev/badge/instructions/shenseanchen/waku-agent/agents-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 | $0.01692 | $0.01692 |
| Opus 5.5 | $0.00677 | $0.00677 |
| Sonnet 5.5 | $0.00338 | $0.00338 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
waku-agent 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 27d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — read this first
Waku is a local-first personal assistant that shows the four pillars behind every serious agent: Harness, Loop, Memory, and Eval/LLM-Ops. It began as a repo you could read in an afternoon and is growing into a full open-source assistant. Every change must keep it clear, honest code a newcomer can follow: the project will get bigger, and it must never get muddier.
This file is for everyone who changes the repo, human or coding agent. A test caps it at 100 lines, so the detail lives in the files it points to.
Before you… read…
| Before you | Read |
|---|---|
| run Waku for the first time | docs/getting-started.md |
| start anything non-trivial | docs/status.md: what works and what is known-broken |
| decide how much process a change needs | conventions §2 |
| add capability (tool, gateway, provider, store) | conventions §3, the footprint ladder |
| add a skill | CONTRIBUTING.md: no Python needed |
| connect Waku Memory, or carry skills to another agent | docs/integrations.md |
| add a tool | the new-tool skill in .claude/skills/new-tool/ |
| run waku for other people on a server | hosted/README.md |
| touch the loop, memory, graph engine or a tool contract | docs/architecture.md, then conventions §2: it may need a proposal |
| change how the dashboard looks | docs/context/design-system.md |
| change dashboard JavaScript or CSS | waku/ops/static/README.md |
| write a doc, UI copy, a commit message or a SKILL.md | docs/context/writing-rules.md |
add a lesson to examples/ or a topic to lab/ |
lab/README.md, then conventions §6 |
| hit something surprising | docs/context/gotchas.md, and add it if it is missing |
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.
- 27d ago Changed · +3 lines · +74 tokens per session 777813394967
- 29d ago Changed · +8 lines · +153 tokens per session 6676e461db71
- 1mo ago Changed · +4 lines · +123 tokens per session 88dbb43888c3
- 1mo ago First seen · 81 lines · 1,342 tokens per session scan A a1e3476f8cb7
waku-agent AGENTS.md is an instructions file published in the GitHub repository ShenSeanChen/waku-agent (2,093 stars, last pushed yesterday), licensed MIT. It adds 1,692 tokens to every session, about $0.0068 per session on Opus 5.5. 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 2026-09-15.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.