pm-agent-review

pm-agent-review is a command for Claude Code from VandanaAjayDubey111/great-pm. It costs 35 tokens per session (868 once invoked), scanned A, original, MIT.

A command that reviews an individual great-pm agent's recent verdicts, such as PASS, FAIL, and NEEDS-WORK. It also shows changes over time and possible drift in the agent's behavior.

In plain words
What is it for?
Use it to audit an agent over a chosen number of past days, such as a reviewer, specification writer, or user researcher.
Why use it?
It makes it easier to see whether an agent is performing consistently instead of judging it from one result.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the great-pm plugin — 10 commands, 48 agents shipped together

Good fit Use it to audit an agent over a chosen number of past days, such as a reviewer, specification writer, or user researcher.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/vandanaajaydubey111/great-pm/pm-agent-review
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/VandanaAjayDubey111/great-pm

Made for: Claude Code.

Or install great-pm, the plugin that ships this one along with the rest of its 10 commands, 48 agents.

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 pm-agent-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-agent-review/github.svg)](https://agentmods.dev/commands/vandanaajaydubey111/great-pm/pm-agent-review)
Your own site
<a href="https://agentmods.dev/commands/vandanaajaydubey111/great-pm/pm-agent-review"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-agent-review/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 pm-agent-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/vandanaajaydubey111/great-pm/pm-agent-review"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-agent-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 868 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 $0.00035 $0.00868
Opus 5 $0.00017 $0.00434
Sonnet 5 $0.00007 $0.00174
Haiku 4.5 $0.00003 $0.00087

Measured 12d ago against content hash 7e0010a179d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pm-agent-review 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 12d 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.

commands/pm-agent-review.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the great-pm /pm-agent-review command. Audit a single great-pm agent's recent behavior.

Parse arguments

  • <agent-name> (required) → e.g. pm-reviewer, spec-writer, user-researcher.
  • --window=<N>days (default: 30) → look-back window.

Pre-flight

AGENT="${1:?usage: /pm-agent-review <agent-name> [--window=<N>days]}"
ls ~/great-pm/agents/${AGENT}.md 2>/dev/null && echo "AGENT_OK" || echo "NO_AGENT"
ls .great-pm/verdicts/ 2>/dev/null && echo "VERDICTS_OK" || echo "NO_VERDICTS"

If NO_AGENT → BLOCKED. List available agents.

Operating procedure

  1. Step 0 — refine the user's query (transparent Mode B). Invoke query-refiner-pm with $ARGUMENTS. The refiner returns:

    You typed:  <original>
    
    Refined to: <refined brief>
    
    What changed: <one line>
    
    Proceeding with refined. Reply "use original" to override.
    

    Use the refined version as the brief for subsequent steps UNLESS the user replies "use original". Log the refinement to .great-pm/refinements/$(date +%Y-%m-%d).log. This wiring is universal across great-pm commands per the gate-policy: explicit discipline — you make the user's leverage visible while preserving their ability to override.

  2. Grep .great-pm/verdicts/*.log for entries by this agent within the window. Collect: timestamp, artefact, verdict, reasoning summary.

  3. Build the distribution:

    == <agent-name> review — last <N> days ==
    
    Total verdicts: <T>
    PASS: <P> (<P%>)
    NEEDS-WORK: <N> (<N%>)
    FAIL: <F> (<F%>)
    
    Trend (by week):
      wk-3: <distribution>
      wk-2: <distribution>
      wk-1: <distribution>
      wk-0: <distribution>
    
  4. Flag drift signals:

    • PASS rate moving up >20% week-over-week → "agent getting more permissive — check rigor".
    • FAIL rate moving up >20% → "agent getting stricter — check prompt or check user inputs got worse".
    • Same artefact-type producing different verdicts → "inconsistency detected; review reasoning".

Read the full file on GitHub · 92 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. 12d ago First seen · 92 lines · 35 tokens per session scan A 7e0010a179d2

Subscribe to this mod's changes

pm-agent-review is a command published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 868 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.