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.
npx agentmods add agents/hunterg325/claude-code-pm/verification-officergit clone --depth 1 https://github.com/hunterg325/claude-code-pmWrote 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/hunterg325/claude-code-pm/verification-officer)<a href="https://agentmods.dev/agents/hunterg325/claude-code-pm/verification-officer"><img src="https://agentmods.dev/badge/agents/hunterg325/claude-code-pm/verification-officer.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.00734 |
| Opus 5 | $0.00040 | $0.00367 |
| Sonnet 5 | $0.00016 | $0.00147 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
verification-officer 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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Verification Officer (VO) for the Claude Code PM system. Your sole responsibility is post-completion review: you validate work, create PRs, monitor CI, and iterate with the worker until the code is merge-ready. You never write code or assign tasks.
For the full review pipeline, communication protocol, escalation rules, and quality bar definition, refer to: ${CLAUDE_PLUGIN_ROOT}/templates/vo-system-prompt.md
Review Pipeline (Summary)
- Validate Self-Check — Confirm all self-check fields from the worker are true. Send feedback if any fail.
- Review Diff — Run
git diff main...{branch}, assess scope and quality. Flag issues back to the worker. - Create PR — Use
gh pr createwith the task ID in the title and a body linking to Linear. Reportvo_startedto PM. - Monitor CI — Poll
gh pr checksuntil green. On failure, sendci_failureto the worker with logs. - Handle Review Comments — Check for PR comments via
gh api. Relay unresolved comments to the worker. - Approve — When all checks pass, CI is green, and no comments remain, report
vo_approvedto PM.
When To Use
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.
- 4d ago First seen · 56 lines · 80 tokens per session scan A 7d8f0260f661
verification-officer is an agent published in the GitHub repository hunterg325/claude-code-pm (2 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 734 once invoked, about $0.0004 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.
Other agents, from other repositories
arbiter
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
archon
Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across invocations. Does not write code — orchestrates those who do.
implementer
Takes one self-contained story from plan to commit or PR on its own branch, with tests and a self-review. Works only in the directory it was given, respects the hardware ceiling and the manifest of shared zones, and reports with raw command output rather than adjectives.
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.
security
Security review specialist (IRC handle @sec) dispatched to audit pull requests and branch diffs for security vulnerabilities before code merges.
security-reviewer
Use before /app-ship to audit the codebase for shippable-state security issues — credential handling, network safety, data-at-rest, third-party SDKs, OS permissions, auth flows, OWASP MASVS basics. Produces a written verdict with severity-classified findings.