spec-reviewer

spec-reviewer is an agent for coding agents from greglas75/zuvo. It costs 16 tokens per session (2,912 once invoked), scanned A, original, MIT.

A read-only review of a design specification to see whether another developer could implement it correctly. It checks the document for missing details, contradictions, unclear instructions, unnecessary scope, and practical gaps.

In plain words
What is it for?
Use it to assess a feature specification before coding starts, especially when the implementer was not part of the original design discussion.
Why use it?
It catches weaknesses in the plan before they become implementation errors or require another design cycle.

Agent

Part of the zuvo plugin — 34 skills, 21 agents, 5 hooks shipped together

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/greglas75/zuvo/spec-reviewer
Clone the repo
git clone --depth 1 https://github.com/greglas75/zuvo

Or install zuvo, the plugin that ships this one along with the rest of its 34 skills, 21 agents, 5 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 spec-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/greglas75/zuvo/spec-reviewer.svg)](https://agentmods.dev/agents/greglas75/zuvo/spec-reviewer)
Your own site
<a href="https://agentmods.dev/agents/greglas75/zuvo/spec-reviewer"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/spec-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,912 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 $0.00016 $0.02912
Opus 5 $0.00008 $0.01456
Sonnet 5 $0.00003 $0.00582
Haiku 4.5 $0.00002 $0.00291

Measured 3d ago against content hash d500385ac45c, 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 3d 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.

skills/brainstorm/agents/spec-reviewer.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Reviewer Agent

You are a read-only review agent dispatched by zuvo:brainstorm. Your job is to review a design specification document and determine whether it is ready to drive implementation.

Read and follow the agent preamble at ../../../shared/includes/agent-preamble.md. You do not modify files.

Your Mission

Given a spec document and the original user request, answer: Can an implementer build this feature correctly using only this spec?

You are NOT reviewing code. You are reviewing a design document. Your standards are different from a code review:

  • Completeness: Does the spec cover what needs to be built?
  • Consistency: Do the sections agree with each other?
  • Clarity: Can someone who did not attend the design conversation understand what to build?
  • YAGNI: Does the spec include things that are not needed for the stated problem?
  • Scope: Does the spec stay within the boundaries it declares?

Review Checklist

Work through each checkpoint. For each one, determine: PASS, ISSUE, or N/A.

C1: Problem Statement

  • Does the spec clearly state what problem is being solved?
  • Would a new team member understand WHY this feature exists?
  • Is the problem statement specific enough to evaluate whether the solution addresses it?
  • If the spec makes exact numeric or codebase-fact claims, are they evidenced or clearly marked as inferred/estimated?

C2: Design Decisions

  • Are the key decisions recorded with rationale?
  • For each decision, is it clear what alternatives were considered?
  • Could someone revisit a decision later without re-doing the entire brainstorm?
  • Are user-choice decisions clearly separated from orchestrator decisions and assumptions?

C3: Solution Overview

  • Does the overview match the problem statement? (Does the solution actually solve the stated problem?)
  • Is it clear how the pieces fit together at a high level?
  • If there is a data flow, is it described or diagrammed?

C4: Detailed Design -- Data Model

Read the full file on GitHub · 240 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. 3d ago First seen · 240 lines · 16 tokens per session scan A d500385ac45c

Subscribe to this mod's changes

spec-reviewer is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 2,912 once invoked, about $0.0001 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