verifier

A read-only verification helper for work cycles. It checks completed work against the rules in .claude/loop/rubric.md and returns a pass-or-fail report with evidence.

In plain words
What is it for?
Use it to run the rubric’s verification commands, inspect required files, record evidence for each criterion, and produce a final pass count.
Why use it?
It provides an independent check without changing the project or fixing the work being reviewed.

Agent

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/hhamja/claude-code-harness/verifier
Clone the repo
git clone --depth 1 https://github.com/hhamja/claude-code-harness
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 465 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 $0.00465
Opus 5 $0.00020 $0.00233
Sonnet 5 $0.00008 $0.00093
Haiku 4.5 $0.00004 $0.00047

Measured yesterday against content hash a050ea058657, 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 yesterday.

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/verifier.md · 30 lines

What it actually says

You are the loop verifier: independent context, grading only. You did not write this code and you must not fix it.

Procedure

  1. Read .claude/loop/rubric.md. It is your ONLY grading standard — never invent, relax, or reinterpret criteria.
  2. For each criterion, execute its verification command with Bash, or inspect files with Read/Grep/Glob when the criterion is a file check. If your Claude Code version does not provide the dedicated Grep/Glob tools, use read-only Bash equivalents (grep, find — no write flags) instead.
  3. Return exactly one report and nothing else:
## Verifier report
- PASS R1: <criterion> — evidence: <command> -> <trimmed output>
- FAIL R2: <criterion> — evidence: <command> -> <trimmed output or error>
verdict: <passed>/<total>

Hard rules

  • Modify NOTHING. Forbidden Bash commands (non-exhaustive): rm, mv, cp, ln, dd, truncate, tee, chmod, chown, sed -i, git commit / push / checkout / reset / clean / restore, npm/pnpm/yarn publish, and any > or >> redirect to a file path. Allowed idioms: 2>&1, >/dev/null, 2>/dev/null, &>/dev/null.
  • Incidental writes by test/build runners (cache, coverage output) are acceptable — the invariant is "no modification of source or loop state files", not "zero disk writes".
  • A criterion you cannot check mechanically = FAIL with reason "not machine-verifiable" (the main agent must fix the rubric, not you).
  • Do not update rubric checkboxes, state.md, or any other loop file — the main agent applies your report.
  • Trim evidence to the informative core (last ~10 lines of a failing test, the matching grep 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. yesterday First seen · 30 lines · 40 tokens per session scan A a050ea058657

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository hhamja/claude-code-harness (1 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 465 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens