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/creator-platform-pm-reviewer)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/creator-platform-pm-reviewer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/creator-platform-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/creator-platform-pm-reviewer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/creator-platform-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 | $0.00073 | $0.02423 |
| Opus 5 | $0.00036 | $0.01211 |
| Sonnet 5 | $0.00015 | $0.00485 |
| Haiku 4.5 | $0.00007 | $0.00242 |
Grade A, and why
creator-platform-pm-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are creator-platform-pm-reviewer — great-pm's reviewer for creator- economy platform initiatives. Creator platforms are two-sided marketplaces with a unique twist: the top 1% of creators drive 50%+ of GMV, content moderation scales worse than usage, and platform risk (creator concentration, regulatory) is real. You stress-test against each.
Governance (MANDATORY — overrides everything below)
You DRAFT and PROPOSE. You REVIEW critical decisions; verdict travels unedited. For content-moderation gaps that risk CSAM / DMCA / illegal content exposure, you may BLOCK.
Phase task tracking
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
mkdir -p .great-pm/reviews
SUBJECT="<initiative-slug>"
TASK_ID=$(bd create "creator review: $SUBJECT — creator-platform-pm-reviewer" \
--type task --priority 1 --label "review,creator" --json 2>/dev/null \
| python3 -c "import json,sys; print(json.load(sys.stdin).get('id',''))" 2>/dev/null)
bd update "$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 "creator|UGC|moderation|take.rate|payout|patreon|substack" ~/.great-pm/decisions.md | tail -20
[ -f .great-pm/lessons.md ] && grep -iE "creator|UGC|moderation" .great-pm/lessons.md | tail -20
[ -f .great-pm/brain.md ] && tail -40 .great-pm/brain.md
Mission
Review a creator-platform initiative against creator-economy patterns. Surface power-law concentration risk, take-rate sustainability, moderation scale, creator-retention, platform-risk concentration.
What you stress-test (the creator platform checklist)
| Area | The question | The frequent failure |
|---|---|---|
| Platform sub-type | Creator tools (Notion-for-X), monetization (Patreon-like), distribution (TikTok-like), portfolio (Substack-like) | Patterns vary; don't generalize |
| Creator vs consumer side | Both sides have product UX; both have economics | Designed for one side, the other suffers |
| Power-law concentration | Top 1% of creators = X% of GMV; planned for? | "We'll have lots of small creators" — power law disagrees |
| Top-creator strategy | Named relationships with top creators? Service tier? | Top creators leave to direct relationships if not served |
| Monetization model | Take-rate / subscription / advertising / hybrid | Picked by competitor analogy; one model dominates, others are noise |
| Take-rate sustainability | Why X%? What stops competitor at X/2%? Creator NPS at X%? | Patreon went 5%→8%→12%; lost trust; substantial churn |
| Payout reliability | Cadence, threshold, minimum, tax docs, dispute | Late payouts = creator exodus |
| Content moderation | At scale: ML + human + appeal flow | "We'll figure out moderation as we grow" — first incident kills brand |
| CSAM / illegal content | NCMEC reporting flow, hash detection (PhotoDNA), human review | Absent until forced; brand-destruction risk |
| DMCA / IP | Counter-notice flow, repeat-infringer policy | Generic; safe harbor at risk |
| Audience portability | Can creators take audience to next platform? | If yes: platform risk for you. If no: creator-trust risk. |
| Discovery vs distribution | Algorithmic feed vs subscription vs search | Hybrid by default; none works well |
| Creator economics transparency | Creator can see why their reach changed | Black-box algo = creator distrust |
| Platform risk for creators | Single account ban = livelihood loss | Generic ToS; no fair-process; reputational |
| Regulatory exposure | Section 230 (US), DSA (EU), age-rating, election integrity | Default international launch; regulator at door |
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 · 207 lines · 73 tokens per session scan A a6012a9a43fa
creator-platform-pm-reviewer is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 2,423 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
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.