waku-agent: Skill for Claude Code

.claude/skills/review-pr/SKILL.md

review-pr is a skill for Claude Code from ShenSeanChen/waku-agent. It costs 93 tokens per session (1,836 once invoked), scanned A, original, MIT.

A guided review process for incoming pull requests and issue reports in the waku-agent project. It presents the situation, its importance, ways to test it together, and whether to merge, reply, or close it.

In plain words
What is it for?
Use it to triage issues, test pull requests with an assistant, and decide what response or action each one needs.
Why use it?
It helps a project maintainer make decisions without reading every code change first, while keeping the final approval in their hands.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is ShenSeanChen/waku-agent's own configuration. It tells Claude Code how to work on waku-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything waku-agent configures →

About the project

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.

ShenSeanChen/waku-agent · 1,720 stars · on GitHub

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ShenSeanChen/waku-agent/main/.claude/skills/review-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ShenSeanChen/waku-agent

Made for: Claude Code.

Wrote 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.

agentmods badge for review-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/shenseanchen/waku-agent/review-pr/github.svg)](https://agentmods.dev/skills/shenseanchen/waku-agent/review-pr)
Your own site
<a href="https://agentmods.dev/skills/shenseanchen/waku-agent/review-pr"><img src="https://agentmods.dev/badge/skills/shenseanchen/waku-agent/review-pr/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.

agentmods 80×15 button for review-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/shenseanchen/waku-agent/review-pr"><img src="https://agentmods.dev/badge/skills/shenseanchen/waku-agent/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,836 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 81
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00093 $0.01836
Opus 5 $0.00046 $0.00918
Sonnet 5 $0.00019 $0.00367
Haiku 4.5 $0.00009 $0.00184

Measured 11d ago against content hash e407f39df059, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-pr 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 11d 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.

.claude/skills/review-pr/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deciding on a PR or an issue, Sean's way

Sean maintains waku-agent solo while a community sends PRs against the good first issue list. He decides fast, without reading diffs, and he is a product manager with a technical background — he wants the decision framed for him AND he wants to be able to see it with his own eyes.

The hard rule, before anything else

NEVER approve, merge, or close a PR without Sean's explicit go-ahead for THAT specific PR. Not "I reviewed it and it's good" — an actual yes from him, per PR, after he has seen the four sections.

Approving a plan that says "drain the queue" is NOT approval to merge. Neither is "go", "sure", or "continue" on a broader task. This was violated on 2026-07-26: six PRs were merged off a plan approval, and Sean had tested none of them himself. His words: "i have not even tested them myself so i am concerned."

Post review comments and change requests freely. Merging is his call.

Frontend and TUI changes are HIS to test

If the diff touches the dashboard frontend (anything under waku/ops/static/ — HTML, CSS, JS) or the TUI/CLI experience, never recommend merge on your own testing. Your screenshots, a clean console and a green suite are not enough evidence for these. Stand the PR up on port 7778 so the live 7777 is untouched, then hand him the URL and say which page to open and what to look for. The fourth section becomes "click this, then tell me to merge."

The dashboard is what he films and what a new user meets first; a layout or copy regression that reads fine to you can be obviously wrong to him. Backend-only changes he is happy to take on your testing.

One item at a time

Never batch. One PR or issue, four sections, then stop and wait for his call. Name people and PRs in words ("@wilenWang's Connections registry"), not bare numbers — he has said plainly that a wall of numbered items is unreadable: "my human brain doesn't have a long context."

Output format — exactly these four sections, in this order

Read the full file on GitHub · 150 lines

Changes

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.

  1. 11d ago First seen · 150 lines · 93 tokens per session scan A e407f39df059

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository ShenSeanChen/waku-agent (1,720 stars, last pushed 13d ago), licensed MIT. It adds 93 tokens to every session and 1,836 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

openclaw-github-dedupe

Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.

vincentkoc/dotskills · 68 tokens

openclaw-pr-batch-sweep

Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes. Use for "next 20", broad contributor PR sweeps, merge-candidate mining, or continued PR-batch work where drafts, maintainer work, trivial…

vincentkoc/dotskills · 95 tokens

github-code-review

Review code changes by analyzing git diffs, leaving inline comments on PRs, and performing thorough pre-push review. Works with gh CLI or falls back to git + GitHub REST API via curl.

moltis-org/moltis · 45 tokens

commit

Prepare and create git commits for dynobox. Use this skill whenever the user asks to commit, create a commit, suggest a commit message, stage changes, or prepare changes for review. Also use it when the user asks whether the changelog should be updated before committing.

dynobox/dynobox · 59 tokens

github

GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…

moltis-org/moltis · 101 tokens

code-review

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…

willdady/platypus · 94 tokens