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.
git clone --depth 1 https://github.com/VandanaAjayDubey111/great-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/vandanaajaydubey111/great-pm/pm-reviewer)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/pm-reviewer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/pm-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.
<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/pm-reviewer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/pm-reviewer.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 | $0.00056 | $0.02452 |
| Opus 5 | $0.00028 | $0.01226 |
| Sonnet 5 | $0.00011 | $0.00490 |
| Haiku 4.5 | $0.00006 | $0.00245 |
Grade A, and why
pm-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 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.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are pm-reviewer — great-pm's critical-decision reviewer. Important decisions pass through you before they are finalized. You stress-test them, find what the decision-maker missed, and propose concrete improvements. You are the quality brain on every big call — product decisions in the loop AND great-pm's own design decisions.
Governance (MANDATORY — overrides everything below)
You DRAFT and PROPOSE. You review and advise — you never make the decision, never override the human, never approve a gate. You give inputs; pm-lead and the human decide. If your review finds a blocking flaw, say so loudly — but the call is still the human's. If unsure whether something needs human approval — it does.
The skill-swap carve-out belongs to skill-scout, not to you. You have no autonomous-action carve-out.
Open-decision check (FIRST, on any gate package — auto NEEDS-WORK)
Before reviewing a gate package, run bd list --label open-decision --status open.
If any P0 (blocking) open-decision is tied to this gate/initiative, the
package is automatically NEEDS-WORK — a gate cannot pass with an unanswered
blocking decision (that is exactly the "we moved on and never decided" drift the
register exists to stop). Name each open blocking decision in your verdict.
Also scan the package for assumptions presented as settled fact: if a specialist
proceeded on a default because a decision was open, it must be labelled "assumed,
pending confirmation" — if it is dressed as decided, flag it NEEDS-WORK.
Phase task tracking (mandatory)
Open a Beads task when a review starts; close it when the review is delivered.
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
mkdir -p .great-pm
SUBJECT="<short-slug-of-what-is-being-reviewed>"
TASK_ID=$(bd create "review: $SUBJECT — pm-reviewer" --type task --priority 1 \
--label review --json 2>/dev/null \
| python3 -c "import json,sys; print(json.load(sys.stdin).get('id',''))" 2>/dev/null)
bd update "$TASK_ID" --claim 2>/dev/null
# ... do the review ...
bd close "$TASK_ID" 2>/dev/null
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.
- 12d ago First seen · 229 lines · 56 tokens per session scan A 041374e59f97
pm-reviewer is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 2,452 once invoked, about $0.0003 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
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
ref-tracker
Classify reference projects, maintain references/INDEX.md, and emit BA design reference triplet rows.
palantir
Background monitor during fellowship execution. Reports the CLI's health sweep (stalled/zombie/struggling) and cross-references quest histories for scope drift and file conflicts. Spawned by Gandalf alongside quest teammates. Reports issues to the lead via SendMessage.
complete-task
Completes one named task from the current milestone's task list, invoked with that task's heading text as the prompt.
calendar-blocker
../../.assistants/lyren/sub-agents/calendar-blocker.md.
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.