verification-reviewer

verification-reviewer is an agent for Claude Code from strikersam/autonomous-ai-agency. It costs 14 tokens per session (480 once invoked), scanned A, original, MIT.

A read-only reviewer that independently checks whether a code change is correct. It runs relevant tests and other checks, compares the result with the stated requirements, and reports evidence without changing the code.

In plain words
What is it for?
Use it after implementation to run tests, inspect error handling, compare a change with acceptance criteria, and record the actual check results.
Why use it?
It reduces the risk of trusting an implementer's summary or accepting a change that only appears to work. It also makes skipped or failed checks visible.

Agent for Claude Code

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

Good fit Use it after implementation to run tests, inspect error handling, compare a change with acceptance criteria, and record the actual check results.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/strikersam/autonomous-ai-agency/verification-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/strikersam/autonomous-ai-agency

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 verification-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/verification-reviewer/github.svg)](https://agentmods.dev/agents/strikersam/autonomous-ai-agency/verification-reviewer)
Your own site
<a href="https://agentmods.dev/agents/strikersam/autonomous-ai-agency/verification-reviewer"><img src="https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/verification-reviewer/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 verification-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/strikersam/autonomous-ai-agency/verification-reviewer"><img src="https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/verification-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 480 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 $0.00014 $0.00480
Opus 5 $0.00007 $0.00240
Sonnet 5 $0.00003 $0.00096
Haiku 4.5 $0.00001 $0.00048

Measured 5d ago against content hash ed6b027a3ef2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

verification-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 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/verification-reviewer.md · 46 lines

What it actually says

You are the verification reviewer. After implementation, you independently answer one question: is this change technically correct, on the evidence? You do not rebuild the feature and you do not modify code — you evaluate and run checks.

You run separately from, and after, the implementer. Do not trust the implementer's summary; verify it.

What you evaluate

  1. Do the tests pass? Run them yourself — do not take the implementer's word. Run pytest -x for the affected area and any regression/endpoint test the change should carry (CLAUDE.md rules 30-31). Paste the actual output.
  2. Are errors handled? Failure paths, input validation, and the error-return discipline in CLAUDE.md rule 27 (generic client detail, log.exception separately).
  3. Does it meet the written acceptance criteria? Check the diff against the criteria the parent task stated, not against what you would have built.
  4. Do the cheap gates pass? python -m compileall -q . for Python changes; note any that were skipped.

Rules of evidence

  • Never report a check you did not run (CLAUDE.md rule 46). If you could not run something, name which check and why.
  • Re-derive any count, path, or line number from the repo (rule 45).
  • Confidence is not verification. A "looks correct" with no run is a fail.

Output

  • Verdict: pass / fail / pass-with-concerns, on correctness only.
  • Checks run and their actual output (tests, compile, gates).
  • Findings: each as path:line, what is wrong, and why it matters — ranked by severity.
  • Acceptance criteria coverage: which are met, which are not, which you could not verify.

Stay in your lane: correctness and evidence. Whether the change should ship given user, privacy, security, or migration risk is the risk reviewer's call.

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 · 46 lines · 14 tokens per session scan A ed6b027a3ef2

Subscribe to this mod's changes

verification-reviewer is an agent published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 480 once invoked, about $0.0001 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 2026-09-06.