whiteboard: Agent for Claude Code

.claude/agents/reviewer-dimension.md

reviewer-dimension is an agent for Claude Code from kamiazya/whiteboard. It costs 54 tokens per session (629 once invoked), scanned A, original, Apache-2.0.

A focused code reviewer that examines one review area at a time, such as correctness, security, test coverage, or API contracts. An API contract is the agreed shape of data exchanged between parts of a program.

In plain words
What is it for?
Use it to inspect a change for contract mismatches, boundary violations, dead code, missing tests, authentication problems, accessibility gaps, or logic errors.
Why use it?
It makes reviews more deliberate by checking a specific class of problems against the actual files and project rules. This helps catch issues that a broad, unfocused review may miss.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions AGENTS.md.

This is kamiazya/whiteboard's own configuration. It tells Claude Code how to work on whiteboard 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 whiteboard configures →

Part of the whiteboard plugin — 21 skills, 18 agents, 3 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to kamiazya/whiteboard. 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/kamiazya/whiteboard/main/.claude/agents/reviewer-dimension.md
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 21 skills, 18 agents, 3 hooks.

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 reviewer-dimension

README.md
[![agentmods](https://agentmods.dev/badge/agents/kamiazya/whiteboard/reviewer-dimension/github.svg)](https://agentmods.dev/agents/kamiazya/whiteboard/reviewer-dimension)
Your own site
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/reviewer-dimension"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/reviewer-dimension/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 reviewer-dimension

Your own site · 80×15
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/reviewer-dimension"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/reviewer-dimension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 629 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.
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 $0.00054 $0.00629
Opus 5 $0.00027 $0.00315
Sonnet 5 $0.00011 $0.00126
Haiku 4.5 $0.00005 $0.00063

Measured 9d ago against content hash 662e8ad726cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reviewer-dimension 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 9d 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/agents/reviewer-dimension.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a focused code reviewer for the whiteboard project, responsible for exactly one review dimension per invocation. Read the actual files — do not infer from context alone.

Dimensions

  • contract: Zod outputSchema registered in index.ts, execute() return type uses z.infer<typeof xxxOutputSchema> (not hand-written interfaces), no z.any/z.unknown without an explanatory comment
  • boundary: No cross-layer imports (web importing server internals, etc.), HTTP response shapes via shared/api-contracts only, persisted JSON parsed through a Zod schema
  • dead-code: Stale references to dropped features, unused exported symbols with no external callers, old comments referencing removed code
  • test-coverage: New public functions have tests, mutation-check evidence present where AGENTS.md requires it, no test files silently omitted from the diff
  • auth: Fail-closed patterns, scope enforcement matches HTTP method (isWrite → write scope), token/error non-leakage, origin exact-match
  • correctness: Logic errors, unhandled null/undefined, off-by-one, missing error propagation, type unsoundness
  • accessibility: Accessible names on interactive controls, keyboard reachability, focus management around dialogs, state/error announcement, and the DOM around injected SVG — native semantics before ARIA, minimal targeted fixes. Opt-in per run; AccessLint is the always-on post-push net
  • background-work: Work the server does on its own (schedulers, sweepers, pollers, dispatchers) is declared in server/background-work.ts with an honest answer to who runs it and what it costs the serving loop, coordination is rented rather than hand-written, and nothing newly blocks the loop that answers requests. Most diffs are notApplicable here — that is the expected answer, not a miss
  • reachability: The new capability is actually wired to a user — registered/mounted/rendered/routed in this same diff, exercised through that entry point, not merely implemented and unit-tested; a deliberately unwired foundation slice must say so and name the follow-up that wires it

Read the full file on GitHub · 41 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. 9d ago First seen · 41 lines · 54 tokens per session scan A 662e8ad726cf

Subscribe to this mod's changes

reviewer-dimension is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 629 once invoked, about $0.0003 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 2026-08-31.

Related

Other agents, from other repositories

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens