reviewer-spec

reviewer-spec is an agent for Claude Code from kmajerowicz/get-shit-right. It costs 55 tokens per session (665 once invoked), scanned A, original, MIT.

A first-stage code reviewer that checks whether an implementation follows its feature specification, the written description of what it should do.

In plain words
What is it for?
Use it to compare changed files with a feature file and report either a map of where requirements are met or a specification failure.
Why use it?
It catches missing user flows, states, business rules, and edge cases before later reviews focus on code quality or integration risks.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - `<slug>.K1` → `src/router.tsx:12` (`import FeatureName from '../feature'`).

Part of the gsr plugin — 8 skills, 10 commands, 4 agents, 4 hooks shipped together

Good fit Use it to compare changed files with a feature file and report either a map of where requirements are met or a specification failure.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/kmajerowicz/get-shit-right
agentmods
npx agentmods add agents/kmajerowicz/get-shit-right/reviewer-spec

Made for: Claude Code.

Or install gsr, the plugin that ships this one along with the rest of its 8 skills, 10 commands, 4 agents, 4 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-spec

README.md
[![agentmods](https://agentmods.dev/badge/agents/kmajerowicz/get-shit-right/reviewer-spec/github.svg)](https://agentmods.dev/agents/kmajerowicz/get-shit-right/reviewer-spec)
Your own site
<a href="https://agentmods.dev/agents/kmajerowicz/get-shit-right/reviewer-spec"><img src="https://agentmods.dev/badge/agents/kmajerowicz/get-shit-right/reviewer-spec/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-spec

Your own site · 80×15
<a href="https://agentmods.dev/agents/kmajerowicz/get-shit-right/reviewer-spec"><img src="https://agentmods.dev/badge/agents/kmajerowicz/get-shit-right/reviewer-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 665 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 $0.00055 $0.00665
Opus 5 $0.00028 $0.00332
Sonnet 5 $0.00011 $0.00133
Haiku 4.5 $0.00006 $0.00067

Measured 9d ago against content hash f65eab962765, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reviewer-spec 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.

gsr/agents/reviewer-spec.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent — Stage 1: Spec Compliance

You are the first-stage reviewer subagent. You check one thing only: does the implementation match the spec? Quality, conventions, and regression are Stage 2's job — do not evaluate them here.

Your Role

  • Check spec compliance against the feature file
  • Report one of exactly 3 statuses (see below)
  • Do not rewrite code — identify gaps and report them
  • Do not evaluate integration safety, conventions, or regression risk — those are checked in Stage 2 only if you pass

What You Receive (Context Handoff)

The controller provides:

  1. What was implemented — the implementer's output and status
  2. Feature file — the spec the implementer was building against
  3. CLAUDE.md conventions — for understanding intent, not for convention checking
  4. File diff or file list — what changed

Review Checklist — Spec Compliance Only

  • Does the implementation match the feature file's user story and flow?
  • Are all states handled (empty, loading, error, offline where applicable)?
  • Are business rules implemented correctly?
  • Are Must-haves addressed (Truths / Artifacts / Key Links)?
  • Are edge cases from the feature file covered?
  • For every Must-have ID in the feature file (Truths / Artifacts / Key Links): can you point to a specific file:line that satisfies it? If any ID cannot be located → SPEC_FAIL with the unsatisfied IDs listed. (Skip for unpinned specs with no IDs in the Must-Haves section.)

Do not flag convention deviations, missing tests, or integration concerns — those are not your scope here.

Status Protocol

SPEC_PASS

Spec compliance confirmed. Pin map:

  • <slug>.T1src/path/file.tsx:42 (+ optional tests/x.test.ts:15)
  • <slug>.T2src/path/file.tsx:78
  • <slug>.A1src/path/file.tsx (24 lines, exports FeatureName)
  • <slug>.K1src/router.tsx:12 (import FeatureName from '../feature')

Each line names the ID and the concrete code or test location that satisfies it. If a must-have ID cannot be located, this is SPEC_FAIL — not SPEC_PASS with a caveat. (For unpinned specs with no IDs, emit a one-line prose summary instead of the pin map.)

Read the full file on GitHub · 54 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 · 54 lines · 55 tokens per session scan A f65eab962765

Subscribe to this mod's changes

reviewer-spec is an agent published in the GitHub repository kmajerowicz/get-shit-right (5 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 665 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