plan-reviewer Claude Code subagentA
plan-reviewer from kamiazya/whiteboard is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.
mdr add kamiazya/whiteboard/.claude/agents/plan-reviewer.md@git:20261002.0803037Pins git:20261002.0803037 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- Claude Code subagent
- Repository
- kamiazya/whiteboard
- Path
.claude/agents/plan-reviewer.md- Versions recorded
- 5
- Latest version
- git:20261002.0803037, committed Oct 2, 2026
- First version recorded
- Jun 15, 2026
- Size
- 5,441 bytes
- Repository stars
- 11
- License
- Apache-2.0
Reviews a draft design/plan for one whiteboard dev task BEFORE implementation, against the repo's completeness rubric. Spawned by the dev-loop workflow's PlanReview gate. Returns pass/fail with concrete must-fix items. Does not write code or verify files exist — it judges plan completeness only.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
You are a plan-review gate for the whiteboard repo. Given a task and its draft design/plan, decide whether implementation can safely start. Judge completeness only — do not implement, and do not just restate the plan. ## Pass criteria (all must hold) 1. **Criteria ↔ tests 1:1**: every completion criterion maps to a concrete, observable test at the correct nearest layer (use the `test-layer-selection` skill: mcp-node / web-jsdom / web-browser / canvas-viewer-browser / E2E). A criterion with no test, or a test with no criterion, is a gap. 2. **High-risk angles present**: negative/error path, contract drift (a Zod schema and a runtime payload travelling separately — see `zod-schema-discipline`), migration/fallback, and race/unmount where the touched surface implies them. 3. **Single coherent scope**: one acceptance boundary and roughly one write scope. Frontend + API + persistence mixed together, or speculative generality, is a fail. 4. **Discipline honored by the plan**: immutability, `getLogger` (no `console.*` in server code), and "red test first" are reflected in the approach. …
Read the whole file at its exact version.
How to install
mdr add kamiazya/whiteboard/.claude/agents/plan-reviewer.md@sha256:f08001f99a94b6d6The line at the top of this page pins the label git:20261002.0803037, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ggkl73lgzpdtgrrp)
1 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in kamiazya/whiteboard/.claude/agents/plan-reviewer.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of plan-reviewer.md from somewhere else? Ask it: where did my plan-reviewer.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 5 versions of this file, between Jun 15, 2026 and Oct 2, 2026, about one every 27 days.
Watch this file (sign in, one email per new version)
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261002.0803037 latest | 2026-10-02 | 0803037 | 5,441 B | A | view · diff |
| git:20260904.b52e20c | 2026-09-04 | b52e20c | 5,440 B | A | view · diff |
| git:20260811.9dea39c | 2026-08-11 | 9dea39c | 4,388 B | A | view · diff |
| git:20260810.892137e | 2026-08-10 | 892137e | 3,642 B | A | view · diff |
| git:20260615.5a9e01c | 2026-06-15 | 5a9e01c | 2,078 B | A | view |
Installed this file, say at plan-reviewer.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (5441 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kamiazya/whiteboard · 11 stars · license Apache-2.0 · pushed 2026-11-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ggkl73lgzpdtgrrp GET https://markdownregistry.com/api/v1/resolve?ref=kamiazya/whiteboard/.claude/agents/plan-reviewer.md GET https://markdownregistry.com/api/v1/blob/f08001f99a94b6d60e24d1ccfd31fded62d7733add9b9d08559aa59d1456bef5
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: which agent file does what.
More from kamiazya/whiteboard
Every file in kamiazya/whiteboard