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.

Install it, pinned
mdr add kamiazya/whiteboard/.claude/agents/plan-reviewer.md@git:20261002.0803037

Pins 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

The exact contents, by fingerprint
mdr add kamiazya/whiteboard/.claude/agents/plan-reviewer.md@sha256:f08001f99a94b6d6

The 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ggkl73lgzpdtgrrp.svg)](https://markdownregistry.com/a/art_ggkl73lgzpdtgrrp)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
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)

versioncommittedcommitsizeaudit
git:20261002.0803037 latest2026-10-02 0803037 5,441 BA view · diff
git:20260904.b52e20c2026-09-04 b52e20c 5,440 BA view · diff
git:20260811.9dea39c2026-08-11 9dea39c 4,388 BA view · diff
git:20260810.892137e2026-08-10 892137e 3,642 BA view · diff
git:20260615.5a9e01c2026-06-15 5a9e01c 2,078 BA view
Check a whole project

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

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • 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

GitHub

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

whiteboard-marketplace Plugin marketplace
kamiazya/whiteboard · .claude-plugin/marketplace.json · Claude Code plugin distribution for the @kamiazya/whiteboard collaborative diagramming MCP. (1 plugin: whiteboard)
v0.0.20 · audit A · 11 stars
architect Claude Code subagent
kamiazya/whiteboard · .claude/agents/architect.md · System-design perspective for the plan-initiative panel. Given an initiative + brief, analyzes seams, data model…
git:20260615.5a9e01c · audit A · 11 stars
codebase-auditor Claude Code subagent
kamiazya/whiteboard · .claude/agents/codebase-auditor.md · Read-only whole-codebase health auditor for ONE dimension (wiring-gaps / architecture / maintainability /…
git:20260823.f4de3fa · audit A · 11 stars
developer Claude Code subagent
kamiazya/whiteboard · .claude/agents/developer.md · TDD implementer for one well-scoped change in the whiteboard repo. Spawned by the dev-loop workflow's Implement phase…
git:20261006.53380bb · audit A · 11 stars
dogfood-persona Claude Code subagent
kamiazya/whiteboard · .claude/agents/dogfood-persona.md · Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface…
git:20261012.6fa4c18 · audit A · 11 stars
marketing Claude Code subagent
kamiazya/whiteboard · .claude/agents/marketing.md · Drafts release notes, changelog entries, README hero/positioning, and announcements for the whiteboard project…
git:20260615.5a9e01c · audit A · 11 stars
product-manager Claude Code subagent
kamiazya/whiteboard · .claude/agents/product-manager.md · Product/value perspective for the plan-initiative panel. Given an initiative + brief, clarifies user value, scope vs…
git:20260615.5a9e01c · audit A · 11 stars
project-manager Claude Code subagent
kamiazya/whiteboard · .claude/agents/project-manager.md · Delivery/sequencing perspective for the plan-initiative panel. Given an initiative + brief, slices the work into…
git:20260811.7b616bf · audit A · 11 stars
qa-scenario Claude Code subagent
kamiazya/whiteboard · .claude/agents/qa-scenario.md · QA tester for one specific scenario (startup/docs-reachability/smoke/error-recovery/migration). Spawned by qa to…
git:20261002.0803037 · audit A · 11 stars
repo-hygiene-investigator Claude Code subagent
kamiazya/whiteboard · .claude/agents/repo-hygiene-investigator.md · Lightweight read-only investigator for repo-hygiene / policy / portability questions — e.g. "should we track .claude/…
git:20260615.5a9e01c · audit A · 11 stars
research-analyst Claude Code subagent
kamiazya/whiteboard · .claude/agents/research-analyst.md · External-research perspective for the plan-initiative panel. Uses web search/fetch to surface industry best practices…
git:20260615.5a9e01c · audit A · 11 stars
reviewer-dimension Claude Code subagent
kamiazya/whiteboard · .claude/agents/reviewer-dimension.md · Focused code reviewer for one specific review dimension (contract/boundary/dead-code/test-coverage/auth/correctness)…
git:20261013.aa963a1 · audit A · 11 stars

Every file in kamiazya/whiteboard

Other files named plan-reviewer

plan-reviewer SKILL.md skill
antonbabenko/deliberation · .agents/skills/plan-reviewer/SKILL.md · Validate that a work plan is executable before work starts.
git:20261008.893bd58 · audit A · 187 stars
plan-reviewer SKILL.md skill
antonbabenko/deliberation · .gemini/skills/plan-reviewer/SKILL.md · Validate that a work plan is executable before work starts.
git:20261008.893bd58 · audit A · 187 stars
plan-reviewer SKILL.md skill
antonbabenko/deliberation · plugins/deliberation/skills/plan-reviewer/SKILL.md · Validate that a work plan is executable before work starts.
git:20261008.893bd58 · audit A · 187 stars

Browse by kind, by grade A, or by owner.