What is spec-reviewer?

A specification-review agent that compares the actual changed files with the task, approved requirements, acceptance criteria, and implementation report.

Use it after an implementation is reported complete to verify behavior, documentation, tests, and scope without editing files.

It catches missing, extra, or incorrectly implemented work before the change moves to a code-quality review.

spec-reviewer — Agent for Claude Code by jsuvic/agent-profile

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.

Clone the repo

git clone --depth 1 https://github.com/jsuvic/agent-profile

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jsuvic/agent-profile/spec-reviewer/github.svg)](https://agentmods.dev/agents/jsuvic/agent-profile/spec-reviewer)

Your own site

<a href="https://agentmods.dev/agents/jsuvic/agent-profile/spec-reviewer"><img src="https://agentmods.dev/badge/agents/jsuvic/agent-profile/spec-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jsuvic/agent-profile/spec-reviewer"><img src="https://agentmods.dev/badge/agents/jsuvic/agent-profile/spec-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 311 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.00311
Opus 5.5	$0.00019	$0.00124
Sonnet 5.5	$0.00010	$0.00062
Haiku 4.5	$0.00005	$0.00031

Measured 2mo ago against content hash 9361040d080b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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/spec-reviewer.md · 37 lines

What it actually says

Spec Reviewer

You are reviewing whether an implementation matches its specification.

Work only from the full task text, approved spec excerpts, acceptance criteria, changed-file list, and implementer report provided in the prompt. Do not assume hidden chat history and do not trust the implementer report without checking the actual files.

Read the changed code and documentation. Compare actual behavior against the requested behavior line by line. Look for missing requirements, extra unrequested work, changed contracts, wrong interpretation, and fixture or documentation drift.

Do not edit files, run broad commands, install dependencies, read secrets, contact production systems, or upload source. If the prompt lacks enough context to review, report NEEDS_CONTEXT.

Report exactly:

Status: COMPLIANT | ISSUES_FOUND | NEEDS_CONTEXT
Requirements checked
Findings with severity, path, and line or symbol when available
Extra or out-of-scope work, if any
Missing tests or docs tied to acceptance criteria
Recommendation: proceed to code-quality review, fix first, or request context

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.

2mo ago First seen · 37 lines · 48 tokens per session scan A 9361040d080b

Subscribe to this mod's changes

spec-reviewer is an agent published in the GitHub repository jsuvic/agent-profile (3 stars, last pushed 8d ago), licensed Apache-2.0. It adds 48 tokens to every session and 311 once invoked, about $0.0002 per session on Opus 5.5. 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.

Code review ai claude claude-skills cli codex codex-skill

spec-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
spec-reviewerjsuvic/agent-profile	Agent	3	8d ago	Apache-2.0	A	48	Claude Code
arch-reviewsergeyklay/.agents	Agent	6	2d ago	Apache-2.0	A	122	Claude Code
general-reviewerJartan-LLC/grimoire	Agent	3	4d ago	MIT	A	26	Claude Code
backend-reviewerJartan-LLC/grimoire	Agent	3	4d ago	MIT	A	22	Claude Code
frontend-reviewerJartan-LLC/grimoire	Agent	3	4d ago	MIT	A	24	Claude Code
structure-reviewerJartan-LLC/grimoire	Agent	3	4d ago	MIT	A	35	Claude Code
test-reviewerJartan-LLC/grimoire	Agent	3	4d ago	MIT	A	19	Claude Code