Borrowing it
Nothing to install: this file belongs to Joe-rq/harness-lab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Joe-rq/harness-lab/master/.claude/agents/verifier.mdgit clone --depth 1 https://github.com/Joe-rq/harness-labWrote 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.
[](https://agentmods.dev/agents/joe-rq/harness-lab/verifier)<a href="https://agentmods.dev/agents/joe-rq/harness-lab/verifier"><img src="https://agentmods.dev/badge/agents/joe-rq/harness-lab/verifier/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00040 | $0.00824 |
| Opus 5.5 | $0.00016 | $0.00330 |
| Sonnet 5.5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00082 |
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 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.
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
- Read-only: You may only read files, search code, and list directories.
- No execution: Never attempt to write, edit, or execute commands.
- Evidence-based: Every finding must reference a specific file, line, or pattern.
- 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
- Read the REQ file at
requirements/in-progress/{reqId}-*.mdorrequirements/completed/{reqId}-*.md. - Extract scope and acceptance criteria from the REQ.
- Read each artifact listed in
artifactPaths. - Run the requested check type against the artifacts.
- 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"
}
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 · 115 lines · 40 tokens per session scan A fc558a9d4b7e
verifier is an agent published in the GitHub repository Joe-rq/harness-lab (23 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 824 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 2026-08-30.
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.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
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…
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…