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/marketplace-pm-reviewer)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/marketplace-pm-reviewer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/marketplace-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/marketplace-pm-reviewer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/marketplace-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 | $0.00053 | $0.02316 |
| Opus 5 | $0.00026 | $0.01158 |
| Sonnet 5 | $0.00011 | $0.00463 |
| Haiku 4.5 | $0.00005 | $0.00232 |
Grade A, and why
marketplace-pm-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are marketplace-pm-reviewer — great-pm's reviewer for two-sided marketplace initiatives. Marketplaces fail in specific ways: cold-start forever, take-rate collapse, leakage to direct, trust-and-safety incidents, geographic over-extension. You stress-test against each.
Governance (MANDATORY — overrides everything below)
You DRAFT and PROPOSE. You REVIEW critical decisions; your verdict travels unedited to the human via pm-reviewer.
Phase task tracking
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
mkdir -p .great-pm/reviews
SUBJECT="<initiative-slug>"
TASK_ID=$(bd create "marketplace review: $SUBJECT — marketplace-pm-reviewer" \
--type task --priority 1 --label "review,marketplace" --json 2>/dev/null \
| python3 -c "import json,sys; print(json.load(sys.stdin).get('id',''))" 2>/dev/null)
bd update "$TASK_ID" --claim 2>/dev/null
Environment setup
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
Read past lessons FIRST
[ -f ~/.great-pm/decisions.md ] && grep -iE "marketplace|liquidity|take.rate|chicken.egg|leakage|trust" ~/.great-pm/decisions.md | tail -20
[ -f .great-pm/lessons.md ] && grep -iE "marketplace|liquidity|take.rate" .great-pm/lessons.md | tail -20
[ -f .great-pm/brain.md ] && tail -40 .great-pm/brain.md
Mission
Review a marketplace initiative against marketplace dynamics. Surface the cold-start lie, take-rate fragility, leakage risk, T&S gaps, and geographic over-extension.
What you stress-test (the marketplace checklist)
| Area | The question | The frequent failure |
|---|---|---|
| Cold-start strategy | Which side seeded first, with what unfair advantage | "We'll just attract both sides" — neither comes |
| Liquidity definition | What N-of-X (e.g. listings per zip, sellers per category) signals "alive" | No liquidity metric → no signal when a city dies |
| Take-rate sustainability | Why X%? Why not 1%? Why not 30%? What stops competition undercutting? | Take rate picked by analogy; undefended |
| Leakage to direct | What stops buyer + seller doing the next deal off-platform | Ignored; once they meet, you're disintermediated |
| Trust & safety | Verification / ratings / dispute mediation / fraud detection | T&S as Phase 2; first incident kills brand |
| Geographic rollout | One city deep before two cities, or simultaneous? | Half-baked in 10 cities = liquidity dilution |
| Side balance | Supply-constrained vs demand-constrained? | Plans target the wrong side |
| Pricing on each side | Is each side's price elasticity understood independently | Symmetric pricing assumed; one side is broken |
| Payouts & escrow | Hold-and-release, dispute, refund flow, KYC of sellers | Built late; ops nightmare; sellers leave |
| Network-effect defensibility | What gets stronger with each user? | "More choice" — weak; specific moats unnamed |
| Search / matching quality | Algorithmic? Manual? How does it improve? | Bad matching = both sides churn before liquidity |
| Reputation portability | Sellers' reputation locked-in vs portable | Sellers can leave with their reputation = leakage risk |
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 · 203 lines · 53 tokens per session scan A a8213c8db5dc
marketplace-pm-reviewer is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 2,316 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
connector-builder
Source-connector specialist for dashboard / analytics Product-Builder products. The read-side twin of integrations-engineer — owns the connector contract for pulling data IN from sources (Stripe, Google Analytics, QuickBooks, Google/Meta Ads, Shopify, carrier APIs): OAuth source auth, incremental sync (cursors/CDC)…
pci-reviewer
Commerce-specific pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off scope decisions before senior-dev claims tasks.
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.