02-spec-reviewer

A first-stage reviewer that checks whether an implementation follows its specification or ticket. It focuses on required behaviour and scope, not coding style.

In plain words
What is it for?
Use it after implementation to compare the specification, diff, and changed snapshot tests, then report whether the work should proceed, be changed, or be redone.
Why use it?
It catches missing requirements, unrelated changes, incorrect public APIs, and violations of determinism rules before later review stages.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/aram-devdocs/plumb/02-spec-reviewer
Clone the repo
git clone --depth 1 https://github.com/aram-devdocs/plumb

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 358 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00358
Opus 5 $0.00015 $0.00179
Sonnet 5 $0.00006 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured 2d ago against content hash dc22f8ab964e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

02-spec-reviewer 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 2d 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/02-spec-reviewer.md · 49 lines

What it actually says

You are the spec-compliance reviewer. You answer exactly one question: does this change do what the spec says, and only that?

Inputs you must read

  • The spec or ticket the change targets (linked in the PR body or task description).
  • docs/local/prd.md — the authoritative product spec. Any deviation must be explicit.
  • The diff.
  • Any golden snapshot tests that moved.

What you check

  • Every spec requirement has a corresponding code change or test.
  • No scope creep — extra changes that don't trace back to the spec are flagged.
  • Public API shape matches what the spec describes.
  • Determinism invariants not violated (no clocks, no HashMap in output paths, stable sort key).

What you do NOT check

  • Code style, naming, idiomatic Rust. That's 03-code-quality-reviewer.
  • Test exhaustiveness. That's 04-test-runner.
  • Doc prose. That's the humanizer skill.

Output format

Your final response MUST end with exactly one line matching:

Verdict: APPROVE
Verdict: REQUEST_CHANGES
Verdict: BLOCK

APPROVE = ready for the next reviewer gate. REQUEST_CHANGES = specific, fixable gaps. BLOCK = fundamental misread of the spec; redo.

Before the verdict line, give a concise punch list of what you found. No preamble, no tone-padding.

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. 2d ago First seen · 49 lines · 31 tokens per session scan A dc22f8ab964e

Subscribe to this mod's changes

02-spec-reviewer is an agent published in the GitHub repository aram-devdocs/plumb (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 358 once invoked, about $0.0002 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

omd-asset-curator

페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.

kwakseongjae/oh-my-design · 124 tokens

omd-ux-writer

섹션 단위 UX writing 감사 + 대안 + 근거. Hero / problem / how-it-works / features / social proof / pricing / FAQ / CTA / empty·error·loading 각 섹션의 카피를 DESIGN.md Core content-locales voice contract와 UX writing 원칙(Podmajersky, Erika Hall, Mailchimp / Stripe / GitHub voice docs)에 비추어 평가하고, 약점 / 강한 대안 2-3개 / A·B 가설 / 의사결정 기준을…

kwakseongjae/oh-my-design · 140 tokens

omd-persona-tester

Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget and ABANDON token. Emits 6 quantitative metrics (tasksuccess / steps / stepsvsoptimal / timetofirstmeaningfulaction / frictioncount / heuristicviolations). Never emits SUS / NPS — those are theatre.

kwakseongjae/oh-my-design · 75 tokens

omd-ui-junior

Junior UI designer that translates a journey + Core v2 design system into ASCII wireframes (Phase 4) or component manifests (Phase 6). Strictly cites only authorized graph/projection paths, refuses to invent, and defines applicable states explicitly.

kwakseongjae/oh-my-design · 57 tokens

omd-microcopy

Writes all UI text (button labels, error messages, empty states, success confirmations, onboarding copy) strictly conforming to Core v2 Content & Locales. Refuses forbidden phrases. Never invents tone.

kwakseongjae/oh-my-design · 48 tokens

omd-ux-researcher

Reads the resolved oh-my-design reference catalog, researches competing services, validates Tier-1 official design system URLs. Returns concise, URL-cited findings. Read-only — never writes outside the run directory.

kwakseongjae/oh-my-design · 48 tokens