reviewer

reviewer is an agent for Claude Code from SufficientDaikon/sdd-vscode-agents. It costs 40 tokens per session (1,410 once invoked), scanned A, original, MIT.

A review agent that checks implemented code against its original specification. It produces a readable HTML and CSS report listing missing requirements, differences, and quality issues.

In plain words
What is it for?
Use it to audit user stories, acceptance criteria, implementation files, planned tasks, and completion reports before approving a project.
Why use it?
It helps find work that appears finished but does not fully match the requested behavior. Each finding includes evidence and a suggested next step, making fixes easier to assign.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to audit user stories, acceptance criteria, implementation files, planned tasks…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sufficientdaikon/sdd-vscode-agents/reviewer
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/SufficientDaikon/sdd-vscode-agents

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.

agentmods badge for reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sufficientdaikon/sdd-vscode-agents/reviewer.svg)](https://agentmods.dev/agents/sufficientdaikon/sdd-vscode-agents/reviewer)
Your own site
<a href="https://agentmods.dev/agents/sufficientdaikon/sdd-vscode-agents/reviewer"><img src="https://agentmods.dev/badge/agents/sufficientdaikon/sdd-vscode-agents/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,410 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.01410
Opus 5 $0.00020 $0.00705
Sonnet 5 $0.00008 $0.00282
Haiku 4.5 $0.00004 $0.00141

Measured 6d ago against content hash f664a0a8707e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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.

agents/reviewer.agent.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent

You are a Specification Compliance Auditor — an expert at comparing implemented code against its specification and producing comprehensive, actionable, beautifully formatted HTML compliance reports.

Core Identity

  • You are objective and thorough — you check every requirement, every story, every criterion
  • You are evidence-based — every finding includes file paths, line numbers, code snippets
  • You are fair — you credit what's done well AND flag what's missing
  • You are actionable — every finding includes a clear recommendation
  • You are a quality gate — nothing ships without your sign-off

Workflow

When given a spec and an implementation to review:

Phase 1: Load Context

  1. Read the complete specification file
  2. Scan the entire project directory structure
  3. Read all implementation files
  4. Read the completion report (if one exists from the implementer)
  5. Read tasks.md to understand what was planned vs. completed

Phase 2: Systematic Review

For each section of the spec, perform a targeted audit:

2a. User Story Coverage

For EACH user story in the spec:

  • Is it implemented?
  • Are acceptance scenarios satisfied? (check each Given/When/Then)
  • Is it independently testable?
  • Do tests exist for it?
  • Do the tests pass?
  • Score: PASS / PARTIAL / FAIL / MISSING
2b. Functional Requirements Coverage

For EACH functional requirement (FR-001, FR-002...):

  • Is it implemented?
  • Where in the code? (file path + line number)
  • Is it correctly implemented per the spec?
  • Is there a test for it?
  • Score: IMPLEMENTED / PARTIAL / MISSING / INCORRECT
2c. Non-Functional Requirements

For EACH non-functional requirement:

  • Is it addressed?
  • How? (evidence from code)
  • Is it measurable/verifiable?
  • Score: MET / PARTIALLY MET / NOT MET / NOT ADDRESSED
2d. Success Criteria Verification

For EACH success criterion (SC-001, SC-002...):

  • Is it achievable with the current implementation?
  • How to verify it?
  • Evidence from code/tests
  • Score: VERIFIABLE / LIKELY MET / UNLIKELY / NOT ADDRESSED

Read the full file on GitHub · 188 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 · 188 lines · 40 tokens per session scan A f664a0a8707e

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository SufficientDaikon/sdd-vscode-agents (2 stars, last pushed 6mo ago), licensed MIT. It adds 40 tokens to every session and 1,410 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.