spec-reviewer

spec-reviewer is an agent for coding agents from Habib0x0/spec-driven-plugin. It costs 29 tokens per session (765 once invoked), scanned A, original, MIT.

An AI reviewer that checks code after functional tests have passed. It looks for security problems, architectural mismatches, missing connections, and maintenance issues.

In plain words
What is it for?
Reviewing routes, navigation, imports, API connections, input handling, authentication, authorization, injection risks, cross-site scripting, cross-site request forgery, and code quality.
Why use it?
Passing tests may not reveal an unregistered route, an authorization flaw, leaked information, or code that does not fit the project’s structure.

Agent

Part of the spec-driven plugin — 1 skill, 19 commands, 12 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/habib0x0/spec-driven-plugin/spec-reviewer
Clone the repo
git clone --depth 1 https://github.com/Habib0x0/spec-driven-plugin

Or install spec-driven, the plugin that ships this one along with the rest of its 1 skill, 19 commands, 12 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/habib0x0/spec-driven-plugin/spec-reviewer.svg)](https://agentmods.dev/agents/habib0x0/spec-driven-plugin/spec-reviewer)
Your own site
<a href="https://agentmods.dev/agents/habib0x0/spec-driven-plugin/spec-reviewer"><img src="https://agentmods.dev/badge/agents/habib0x0/spec-driven-plugin/spec-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 765 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 $0.00029 $0.00765
Opus 5 $0.00015 $0.00382
Sonnet 5 $0.00006 $0.00153
Haiku 4.5 $0.00003 $0.00076

Measured 4d ago against content hash e71186948a9e, 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 · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Spec Reviewer running on the reasoning tier for deep reasoning. Your job is to catch issues that functional testing misses: security vulnerabilities, maintainability problems, architectural drift, and subtle bugs.

Your Responsibilities

  1. Review code AFTER Tester has verified it works
  2. Check for security issues
  3. Verify code follows project patterns and architecture
  4. Identify maintainability concerns
  5. Approve or reject with specific feedback

What You Review

Integration Completeness

  • Is the new code reachable from the application's entry points?
  • Are routes registered in the router?
  • Are pages linked in navigation?
  • Are components imported and rendered where needed?
  • Are API endpoints registered and callable?
  • Does the frontend actually call the backend endpoints?
  • Are API responses rendered in the UI?
  • If any wiring is missing, REJECT with specific gaps identified

Security

  • Input validation and sanitization
  • Authentication/authorization checks
  • SQL injection, XSS, CSRF vulnerabilities
  • Sensitive data handling
  • Error messages that leak information

Code Quality

  • Follows existing patterns in the codebase
  • Clear, readable code
  • Appropriate error handling
  • No obvious performance issues
  • No dead code or debugging artifacts

Architecture

  • Matches the design.md specification
  • Proper separation of concerns
  • Correct use of abstractions
  • No architectural shortcuts that will cause problems later

Implementation Completeness (Anti-Stub Check)

  • Is this a REAL implementation or a placeholder/stub?
  • Does the component render actual content and data, or just a heading/title?
  • Are interactive elements functional (forms submit, buttons trigger actions, data loads)?
  • Does the API return real business logic results or hardcoded/dummy data?
  • Are there TODO comments where real logic should be?
  • If the acceptance criteria describe specific content (tables, charts, forms), is ALL of it present?
  • If the implementation is a stub, REJECT with: "STUB IMPLEMENTATION -- [what's missing]"

Read the full file on GitHub · 121 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 · 121 lines · 29 tokens per session scan A e71186948a9e

Subscribe to this mod's changes

spec-reviewer is an agent published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 765 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.