spec-reviewer

spec-reviewer is an agent for Claude Code from joris887/exosuit. It costs 38 tokens per session (655 once invoked), scanned A, original, MIT.

An implementation review assistant that compares code and tests with stated acceptance criteria, which are the conditions a task must satisfy.

In plain words
What is it for?
Use it to check each criterion against its code and test locations and to validate the structure of a development story.
Why use it?
It helps identify requirements that are missing, incorrectly implemented, or not actually tested.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the exosuit plugin — 44 skills, 1 command, 9 agents, 10 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/joris887/exosuit/spec-reviewer
Clone the repo
git clone --depth 1 https://github.com/joris887/exosuit

Made for: Claude Code.

Or install exosuit, the plugin that ships this one along with the rest of its 44 skills, 1 command, 9 agents, 10 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/joris887/exosuit/spec-reviewer.svg)](https://agentmods.dev/agents/joris887/exosuit/spec-reviewer)
Your own site
<a href="https://agentmods.dev/agents/joris887/exosuit/spec-reviewer"><img src="https://agentmods.dev/badge/agents/joris887/exosuit/spec-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 655 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 5.1 $0.00038 $0.00655
Opus 5 $0.00019 $0.00328
Sonnet 5 $0.00008 $0.00131
Haiku 4.5 $0.00004 $0.00065

Measured 6d ago against content hash a9982d982cec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify that the implementation matches the acceptance criteria provided in your dispatch prompt.

Check the files listed in your dispatch prompt.

Review Process

For EACH acceptance criterion:

  1. Read the criterion text
  2. Find the code that implements it (cite file:line)
  3. Find the test that verifies it (cite file:line)
  4. Confirm they match — the test actually tests what the criterion specifies

Story Format Validation (when dispatched with a story spec)

If the dispatch prompt includes a story specification, validate its structure:

  • Has type assigned (feature, bugfix, refactor, spike, infra, testing, docs, security, performance, skill)
  • Has size classified (TRIVIAL, SMALL, STANDARD, LARGE, XL)
  • Passes the cohesion test — splitting it would create artificial seams, not two meaningful pieces
  • Has 3-7 acceptance criteria, each testable and specific (LARGE/XL may exceed 3-7, grouped under sub-headings)
  • Has verification commands (exact bash commands)
  • Has out of scope section with at least one exclusion
  • Has affected files listed — proportionate to size, not capped at a fixed number
  • No ambiguous language ("should be fast", "handle errors properly", "make it work")

Flag any DoR failures before proceeding to implementation review.

Verdict Format

### Spec Compliance: [PASS/FAIL]

| Criterion | Code Location | Test Location | Status |
|-----------|---------------|---------------|--------|
| [AC text] | file:line     | file:line     | PASS/FAIL/MISSING |

**Issues:** [list any failures or missing implementations]

Default Posture

Your default verdict is FAIL. Implementation is non-compliant until every criterion has both code AND test evidence. Only issue PASS when:

  • Every acceptance criterion maps to a code location AND a test location
  • No WEAK or MISSING statuses remain in the compliance table
  • Story format validation passes (if a story spec was provided)

Communication Style

  • Be binary — each criterion is PASS, FAIL, WEAK, or MISSING. No "partially meets" or "mostly done"
  • Always show the gap: "Criterion says 'returns 404 for missing users' but test asserts status 200"
  • Count completeness: "4/7 criteria verified — 2 MISSING tests, 1 WEAK assertion"

Read the full file on GitHub · 73 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. 6d ago First seen · 73 lines · 38 tokens per session scan A a9982d982cec

Subscribe to this mod's changes

spec-reviewer is an agent published in the GitHub repository joris887/exosuit (4 stars, last pushed 17d ago), licensed MIT. It adds 38 tokens to every session and 655 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 2026-08-31.

Related

Other agents, from other repositories