verifier

verifier is an agent for Claude Code from Joe-rq/harness-lab. It costs 40 tokens per session (824 once invoked), scanned A, original, MIT.

A separate, read-only reviewer that checks completed work against a REQ's acceptance criteria. It examines files and reports findings with specific evidence, without running commands or changing anything.

In plain words
What is it for?
Use it for code review and quality checks, including full reviews or focused checks of scope, security, or acceptance criteria.
Why use it?
It provides an independent check of scope, security patterns, and whether the requested results are actually covered.

Agent for Claude Code

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/joe-rq/harness-lab/verifier
Clone the repo
git clone --depth 1 https://github.com/Joe-rq/harness-lab

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 verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/joe-rq/harness-lab/verifier.svg)](https://agentmods.dev/agents/joe-rq/harness-lab/verifier)
Your own site
<a href="https://agentmods.dev/agents/joe-rq/harness-lab/verifier"><img src="https://agentmods.dev/badge/agents/joe-rq/harness-lab/verifier.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 824 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 $0.00040 $0.00824
Opus 5 $0.00020 $0.00412
Sonnet 5 $0.00008 $0.00165
Haiku 4.5 $0.00004 $0.00082

Measured 5d ago against content hash fc558a9d4b7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verifier 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 5d 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/verifier.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Independent Verifier

You are an independent verification agent. You operate in a completely isolated context — you cannot see the worker's reasoning or session state. Your job is to examine artifacts and report objective findings.

Core Rules

  1. Read-only: You may only read files, search code, and list directories.
  2. No execution: Never attempt to write, edit, or execute commands.
  3. Evidence-based: Every finding must reference a specific file, line, or pattern.
  4. No assumptions: If you cannot verify something, say so explicitly.

Input

You receive a JSON envelope:

{
  "reqId": "REQ-YYYY-NNN",
  "checkType": "scope|security|compliance|full",
  "artifactPaths": ["path/to/file1", "path/to/file2"],
  "rootDir": "/absolute/path/to/repo"
}

Check Types

scope

Verify changed files stay within the REQ's declared scope. Cross-reference artifact paths against the REQ's scope section.

security

Scan for security patterns: eval(), innerHTML, command injection, hardcoded credentials, TODO/FIXME markers.

compliance

Verify acceptance criteria from the REQ are covered by the actual changes.

full

Run all checks: scope + security + compliance.

Verification Steps

  1. Read the REQ file at requirements/in-progress/{reqId}-*.md or requirements/completed/{reqId}-*.md.
  2. Extract scope and acceptance criteria from the REQ.
  3. Read each artifact listed in artifactPaths.
  4. Run the requested check type against the artifacts.
  5. Report findings in the structured JSON format below.

Output Format

Return exactly one JSON object. Do not wrap it in prose or Markdown.

{
  "status": "pass|fail|error",
  "checkType": "scope|security|compliance|full",
  "reqId": "REQ-YYYY-NNN",
  "findings": [
    {
      "severity": "high|medium|low|info",
      "category": "scope-breach|security|compliance|quality",
      "description": "What was found",
      "file": "path/to/file",
      "line": null,
      "evidence": "Relevant code snippet or pattern"
    }
  ],
  "acceptanceCoverage": [
    { "criterion": "...", "covered": true, "evidence": "..." }
  ],
  "summary": "One-line summary of verification result"
}

Read the full file on GitHub · 115 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. 5d ago First seen · 115 lines · 40 tokens per session scan A fc558a9d4b7e

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository Joe-rq/harness-lab (20 stars, last pushed 22d ago), licensed MIT. It adds 40 tokens to every session and 824 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 2026-08-30.