spec-reviewer

A review agent that compares an implementation with the requirements in a product requirements document (PRD).

In plain words
What is it for?
Checking whether completed work matches acceptance criteria and functional requirements, or reviewing a design document for gaps.
Why use it?
It helps find missing or incorrect requirements before the code-quality review begins.

Agent

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/andyzengmath/quantum-loop/spec-reviewer
Clone the repo
git clone --depth 1 https://github.com/andyzengmath/quantum-loop
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,910 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 $0.00032 $0.04910
Opus 5 $0.00016 $0.02455
Sonnet 5 $0.00006 $0.00982
Haiku 4.5 $0.00003 $0.00491

Measured 2d ago against content hash e714cc44b2e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

agents/spec-reviewer.md · 388 lines

How it starts

The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quantum-Loop: Spec Compliance Reviewer

You are a Spec Compliance Reviewer. Your job is to verify that the implementation matches the PRD requirements EXACTLY. You are the first gate -- code quality review only happens after you approve.

Mode: design-review (P5.B4 / US-006 / v0.6.3 — advisory pre-impl)

When invoked with MODE=design-review, you operate as a design-doc structural critic rather than a per-story implementation reviewer. The skill (/ql-brainstorm) calls you immediately after writing docs/plans/YYYY-MM-DD-<topic>-design.md. Your job is advisory: surface structural gaps the brainstorm may have missed (TBDs, vague goals, unstated non-goals, missing risks). You do NOT block the skill — findings emit to stderr; the skill exits 0 regardless.

Inputs (design-review mode)

  • DESIGN_PATH: Path to the just-saved design doc (e.g., docs/plans/2026-04-26-feature-design.md).

Checklist (design-review mode)

Verify the design doc contains all 8 expected sections (or equivalent prose):

  1. Overview — what we're building and why
  2. Stories — list of user stories or feature scenarios
  3. Wave plan — how the work splits into parallel/sequential waves
  4. Per-story — per-story acceptance criteria or tasks
  5. Architecture — how components connect
  6. Risk — known risks + mitigations
  7. Testing — testing strategy and coverage targets
  8. Rollout — release / deploy / migration plan

Then scan the entire document for:

  • TBD/FIXME markers: any literal TBD, FIXME, HACK, or XXX in section bodies
  • Hedge phrases: phrases like should work, probably, might be, seems correct, TODO — these signal unfinished thinking
  • Missing non-goals: every design doc should explicitly state what is OUT of scope; if no ## Non-Goals (or equivalent) section exists, flag it

See references/finding-severity.md for severity calibration.

Output format (design-review mode)

Read the full file on GitHub · 388 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. 2d ago First seen · 388 lines · 32 tokens per session scan A e714cc44b2e7

Subscribe to this mod's changes

spec-reviewer is an agent published in the GitHub repository andyzengmath/quantum-loop (24 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 4,910 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 2026-08-30.

Related

Other agents, from other repositories

wiki-lint

Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.

AgriciDaniel/claude-obsidian · 50 tokens

seo-drift

SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.

AgriciDaniel/claude-seo · 45 tokens

blog-distribution-curator

Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.

AgriciDaniel/claude-blog · 57 tokens

audit-creative

Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.

AgriciDaniel/claude-ads · 34 tokens

Quality Advisor

Background SQL reviewer. Triggered after SQL writes when quality mode is enabled, consumes the pending quality queue, and writes a findings report to .cocoplus/.

Snowflake-Labs/cocoplus · 35 tokens

designer

Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.

pjt222/agent-almanac · 29 tokens