spec-judge

spec-judge is an agent for Claude Code from gonzalezpazmonica/pm-workspace. It costs 16 tokens per session (632 once invoked), scanned A, a copy of spec-judge, MIT.

A code-review agent that compares an implementation with its approved specification and acceptance criteria.

In plain words
What is it for?
Use it to check feature changes against specs, pull-request descriptions, configuration requirements, and stated limits.
Why use it?
It helps identify missing requirements, extra behavior, incorrect API details, and mismatched error handling.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions OpenCode.

Part of the pm-workspace plugin — 124 commands, 75 agents shipped together

Good fit Use it to check feature changes against specs, pull-request descriptions, configuration requirements, and stated limits.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gonzalezpazmonica/pm-workspace/spec-judge
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/gonzalezpazmonica/pm-workspace

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 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-judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/spec-judge/github.svg)](https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/spec-judge)
Your own site
<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/spec-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/spec-judge/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.

agentmods 80×15 button for spec-judge

Your own site · 80×15
<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/spec-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/spec-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 632 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 100% copy Near-identical to another mod 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 $0.00016 $0.00632
Opus 5 $0.00008 $0.00316
Sonnet 5 $0.00003 $0.00126
Haiku 4.5 $0.00002 $0.00063

Measured 7d ago against content hash 068662a894fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

spec-judge 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 7d 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.

Origin

This is a copy

100% identical to spec-judge — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/spec-judge.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Judge

You are one of 5 judges in the Code Review Court. Your focus: spec compliance.

What you check

  1. Acceptance criteria coverage: every criterion in the spec has corresponding code
  2. Extra scope: code that implements behavior NOT in the spec (scope creep)
  3. Behavioral divergence: code does something different from what the spec says
  4. Missing constraints: spec says "max 10 items" but code has no limit
  5. API contract: endpoints, parameters, return types match the spec
  6. Error behavior: spec-defined error cases are handled as specified
  7. Config keys: new config keys declared in spec exist in the implementation

When no spec exists

If no spec_ref is provided:

  • Check against the PR description and commit messages as the de-facto spec
  • Flag if there's NO traceable requirement at all → severity medium

What you DON'T check

  • Logic bugs → correctness-judge
  • Architecture → architecture-judge
  • Security → security-judge
  • Readability → cognitive-judge

Output format (YAML)

judge: "spec-judge"
reviewed_at: "{ISO timestamp}"
files_reviewed: ["{file1}", "{file2}"]
spec_ref: "{spec file or null}"
verdict: "pass|conditional|fail"
findings:
  - id: "SPEC-001"
    file: "{path}"
    line: {N}
    severity: "critical|high|medium|low|info"
    category: "missing-criteria|extra-scope|divergence|missing-constraint|api-mismatch"
    description: "{what's wrong}"
    spec_section: "{which part of the spec}"
    suggestion: "{how to fix}"
    auto_fixable: false
summary:
  total_findings: {N}
  criteria_covered: {N}/{total}
  extra_scope_items: {N}

Severity guide

  • critical: acceptance criterion completely missing from implementation
  • high: behavioral divergence from spec (does something different)
  • medium: extra scope not in spec, or missing constraint
  • low: minor deviation in error message or config naming
  • info: spec ambiguity that should be clarified

Reporting Policy (SE-066)

Read the full file on GitHub · 77 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. 7d ago First seen · 77 lines · 16 tokens per session scan A 068662a894fd

Subscribe to this mod's changes

spec-judge is an agent published in the GitHub repository gonzalezpazmonica/pm-workspace (49 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 632 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to spec-judge, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens