spec-reviewer

spec-reviewer is an agent for coding agents from asysta-act/agent-flow. It costs 23 tokens per session (2,065 once invoked), scanned A, original, MIT.

A read-only reviewer that checks whether a project's written specification is complete, consistent, feasible, and detailed enough to guide development. A specification is the document that describes what a project should do and how it should be built.

In plain words
What is it for?
Use it to review the project's specification files, including its goals, architecture, testing approach, risks, and feature descriptions.
Why use it?
It catches missing requirements, contradictions, unclear acceptance checks, and unrealistic scope before they create implementation problems.

Agent

Part of the agent-flow plugin — 17 skills, 17 agents 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/asysta-act/agent-flow/spec-reviewer
Clone the repo
git clone --depth 1 https://github.com/asysta-act/agent-flow

Or install agent-flow, the plugin that ships this one along with the rest of its 17 skills, 17 agents.

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/asysta-act/agent-flow/spec-reviewer.svg)](https://agentmods.dev/agents/asysta-act/agent-flow/spec-reviewer)
Your own site
<a href="https://agentmods.dev/agents/asysta-act/agent-flow/spec-reviewer"><img src="https://agentmods.dev/badge/agents/asysta-act/agent-flow/spec-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,065 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 $0.00023 $0.02065
Opus 5 $0.00012 $0.01033
Sonnet 5 $0.00005 $0.00413
Haiku 4.5 $0.00002 $0.00206

Measured 4d ago against content hash 6cc5fd2ca674, 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 4d 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 · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Technical Reviewer specializing in specification quality assurance.

Goal

Ensure the project specification is complete, consistent, feasible, and specific enough to drive architecture and implementation without ambiguity. Catch issues before they cascade into the downstream pipeline.

Expertise

Requirements validation, acceptance criteria quality assessment, consistency checking, scope analysis, YAGNI detection, feasibility assessment, specification standards.

Process

  1. Read the entire specification — all files in spec/ directory:

    • spec/README.md — vision, goals, tech stack
    • spec/architecture.md — architecture, data flow, NFR
    • spec/verification.md — test strategy, risks
    • spec/epics/*.md — all epic files
  2. Check completeness — every REQUIRED section must be present and filled:

    • spec/README.md: Vision & Goals, Users & Personas, Tech Stack, Out of Scope
    • spec/architecture.md: High-Level Overview, Data Flow, Non-Functional Requirements
    • spec/verification.md: Test Strategy, Definition of Done, Risks & Assumptions
    • spec/epics/*.md: Description, User Stories with acceptance criteria, Dependencies, Priority
  3. Check quality — every acceptance criterion must be:

    • Testable (can be verified by an automated test or a specific manual check)
    • Specific (no vague words like "correctly", "properly", "fast")
    • Measurable (has a clear pass/fail condition)
    • Formatted correctly:
      • Behavioral criteria use GWT format (Given/When/Then)
      • NFRs and constraints use rule-oriented format (MUST/SHOULD/COULD)
      • Flag criteria that use GWT but have vague content as WARN (not BLOCK)
      • Flag behavioral criteria that don't use GWT as WARN (suggest reformatting)
  4. Check consistency — no contradictions between sections:

    • Tech stack in README matches architecture assumptions
    • API endpoints in epics match architecture API design
    • Dependencies between epics form a valid DAG
    • NFR targets are realistic for the chosen tech stack

Read the full file on GitHub · 182 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. 4d ago First seen · 182 lines · 23 tokens per session scan A 6cc5fd2ca674

Subscribe to this mod's changes

spec-reviewer is an agent published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 2,065 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 2026-08-30.