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/plugins/vandanaajaydubey111/great-pm/great-pm)<a href="https://agentmods.dev/plugins/vandanaajaydubey111/great-pm/great-pm"><img src="https://agentmods.dev/badge/plugins/vandanaajaydubey111/great-pm/great-pm/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/plugins/vandanaajaydubey111/great-pm/great-pm"><img src="https://agentmods.dev/badge/plugins/vandanaajaydubey111/great-pm/great-pm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
great-pm scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"command": "INPUT=$(cat 2>/dev/null); if [ -z \"$INPUT\" ]; then exit 0; fi; CMD=$(echo \"$INPUT\" | python3 -c \"import sys,json; d=json.load(sys.stdin); print(d.get('tool_input',{}).get('command',''))\" 2>/dev/null); i How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "great-pm",
"description": "A full product team for a solo PM or founder. Specialist agents run the product loop — discovery, strategy, prioritization, specs, launch, measurement — while the human confirms a small number of gates.",
"version": "1.0.0",
"author": { "name": "Vandana Dubey", "url": "https://github.com/VandanaAjayDubey111" },
"license": "MIT",
"keywords": ["product-management", "ai-pm", "multi-agent", "orchestration", "claude-code-plugin"],
"hooks": {
"SessionStart": [
{
"matcher": null,
"hooks": [
{
"type": "command",
"command": "bash \"${CLAUDE_PLUGIN_ROOT:-$HOME/great-pm}/scripts/great-pm-session-start.sh\"",
"timeout": 20,
"statusMessage": "Loading great-pm context..."
}
]
}
],
"SubagentStart": [
{
"matcher": null,
"hooks": [
{
"type": "command",
"command": "if [ -f .great-pm/PROJECT.md ]; then echo '=== PROJECT.md (top) ==='; head -25 .great-pm/PROJECT.md; fi; if [ -f .great-pm/brain.md ]; then echo ''; echo '=== brain.md (last 40 lines — recent synthesis) ==='; tail -40 .great-pm/brain.md; fi; if [ -f .great-pm/HANDOFF.md ]; then echo ''; echo '=== HANDOFF.md (recent) ==='; tail -20 .great-pm/HANDOFF.md; fi; if [ -d .great-pm/verdicts ]; then echo ''; echo '=== Latest verdicts (3 most recent files) ==='; ls -t .great-pm/verdicts/*.log 2>/dev/null | head -3 | xargs tail -2 2>/dev/null | head -10; fi; exit 0",
"timeout": 5,
"statusMessage": "Injecting great-pm brain context..."
}
]
}
],
"PreCompact": [
{
"matcher": null,
"hooks": [
{
"type": "command",
"command": "mkdir -p .great-pm; BRANCH=$(git branch --show-current 2>/dev/null || echo unknown); LAST_COMMIT=$(git log --oneline -1 2>/dev/null || echo none); UNCOMMITTED=$(git status --short 2>/devWhat it installs
The manifest is a name and a version. 10 commands, 48 agents travel with it, and installing the plugin installs all of them — 3,595 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command pm-agent-retire A 44 tokens
- Command pm-audit A 61 tokens
- Command pm-discover A 43 tokens
- Command pm-agent-review A 35 tokens
- Command pm-board A 46 tokens
- Command pm-competitive A 31 tokens
- Command pm-cost A 43 tokens
- Command pm-crystallize A 48 tokens
- Command pm-burn A 33 tokens
- Command pm-digest A 35 tokens
- Agent grill-me A 204 tokens
- Agent pm-lead A 54 tokens
- Agent ai-launch-strategist A 64 tokens
- Agent skill-scout A 89 tokens
- Agent ai-cost-optimizer A 47 tokens
- Agent ai-ethics-pm A 54 tokens
- Agent ai-experimentation-pm A 55 tokens
- Agent ai-feedback-loop-designer A 59 tokens
- Agent ai-product-strategist A 60 tokens
- Agent ai-roadmap-planner A 50 tokens
- Agent ai-rollback-strategist A 56 tokens
- Agent ai-safety-pm A 55 tokens
- Agent analytics-analyst A 49 tokens
- Agent b2b-saas-pm-reviewer A 62 tokens
- Agent consumer-app-pm-reviewer A 64 tokens
- Agent continuous-learner A 67 tokens
- Agent creator-platform-pm-reviewer A 73 tokens
- Agent data-strategist A 44 tokens
- Agent edtech-pm-reviewer A 79 tokens
- Agent enterprise-saas-pm-reviewer A 69 tokens
- Agent experiment-designer A 46 tokens
- Agent fintech-pm-reviewer A 76 tokens
- Agent harness-engineer-pm A 65 tokens
- Agent healthcare-pm-reviewer A 78 tokens
- Agent marketplace-pm-reviewer A 53 tokens
- Agent mlops-pm A 47 tokens
- Agent model-evaluator-pm A 49 tokens
- Agent pm-auditor A 85 tokens
- Agent pm-reviewer A 56 tokens
- Agent prompt-engineer-pm A 71 tokens
- Agent query-refiner-pm A 63 tokens
- Agent spec-writer A 56 tokens
- Agent stakeholder-comms A 54 tokens
- Agent tradeoff-arbiter A 62 tokens
- Agent feedback-synthesizer A 53 tokens
- Agent gtm-strategist A 54 tokens
- Agent launch-manager A 47 tokens
- Agent market-analyst A 49 tokens
- Agent metrics-architect A 53 tokens
- Agent pm-advisor A 123 tokens
- Agent pricing-strategist A 49 tokens
- Agent prioritization-analyst A 69 tokens
- Agent product-strategist A 45 tokens
- Agent roadmap-planner A 48 tokens
- Agent spec-reviewer A 56 tokens
- Agent strategy-analyst A 109 tokens
- Agent user-researcher A 47 tokens
- Agent devils-advocate B 159 tokens
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 87 lines scan A 2c7aedd6c6f2
great-pm is a plugin published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
arrow-maintenance
Scaling layer for linked-intent-dev. Tracks spec-to-code coherence across large projects via docs/arrows/ index. Includes brownfield bootstrap for mapping existing codebases.
pm
GitHub issue lifecycle: brainstorm design approaches, create structured issues for LLM agent teams, triage and recommend next issues, audit and clean up stale backlogs, and deep-validate individual issues against the codebase.
debt-ops
Every shortcut your coding agent takes, saved to your repo as it happens. Fix them when you're ready.
polisade
Polisade Orchestrator — autonomous development framework by Polisade. Claude operates as a full dev team: implement → test → PR → review → merge. (Technical id: polisade).
agent-traffic-control
Coordination toolkit for parallel Claude Code sessions sharing one repo — issue-pickup claim protocol (assignee + wip label), worktree & session-isolation pitfalls, parallel-PR conflict recovery, subagent-integrity edge cases, and squash/merge mechanics for parallel-PR workflows. Plus resume-gate, an opt-in hook that…
milestone-driver
Drives a GitHub milestone to completion: triages each issue for design gaps + dependency order up front, then for each buildable issue finds the root cause (or parks it), dispatches a TDD implementer subagent, runs unit + E2E tests + code review, opens a PR, and auto-merges issues on CI green. The whole loop sits…