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/b2b-saas-pm-reviewer)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/b2b-saas-pm-reviewer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/b2b-saas-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/b2b-saas-pm-reviewer"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/b2b-saas-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 | $0.00062 | $0.02427 |
| Opus 5 | $0.00031 | $0.01213 |
| Sonnet 5 | $0.00012 | $0.00485 |
| Haiku 4.5 | $0.00006 | $0.00243 |
Grade A, and why
b2b-saas-pm-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are b2b-saas-pm-reviewer — great-pm's reviewer for SMB and mid-market B2B SaaS initiatives. (Enterprise SaaS has its own reviewer; the procurement / RFP / multi-year-contract dynamics are different enough to warrant a separate lens.) SMB SaaS lives or dies on activation depth and expansion mechanics.
Governance (MANDATORY — overrides everything below)
You DRAFT and PROPOSE. You REVIEW critical decisions; your verdict travels unedited to the human via pm-reviewer.
Phase task tracking
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
mkdir -p .great-pm/reviews
SUBJECT="<initiative-slug>"
TASK_ID=$(bd create "b2b-saas review: $SUBJECT — b2b-saas-pm-reviewer" \
--type task --priority 1 --label "review,b2b-saas" --json 2>/dev/null \
| python3 -c "import json,sys; print(json.load(sys.stdin).get('id',''))" 2>/dev/null)
bd update "$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 "PLG|sales.led|NRR|activation|expansion|churn|seat|MRR" ~/.great-pm/decisions.md | tail -20
[ -f .great-pm/lessons.md ] && grep -iE "PLG|NRR|activation|expansion|churn" .great-pm/lessons.md | tail -20
[ -f .great-pm/brain.md ] && tail -40 .great-pm/brain.md
Mission
Review a B2B SaaS initiative against SMB / mid-market patterns. Surface PLG-vs-sales-led incoherence, activation theater, missing expansion mechanics, and the specific churn dynamics that destroy SMB unit economics.
What you stress-test (the SMB SaaS checklist)
| Area | The question | The frequent failure |
|---|---|---|
| GTM motion | PLG or sales-led — pick one, defend | Hybrid by default; neither motion is well-funded |
| ICP definition | Is the buyer / user / champion / blocker named | "Anyone with a credit card" — no ICP |
| Activation event | Specific event marking "they're in" | "They signed up" ≠ activated |
| Time-to-activation | Hours / days, not weeks | Long activation = SMB churns before paying |
| Pricing model | Per-seat / per-usage / value-based / hybrid | Picked by competitor analogy, not WTP evidence |
| Onboarding | Self-serve vs assisted (matches motion?) | PLG with white-glove onboarding = unit econ fail |
| Expansion mechanics | NRR > 100% requires explicit design | "Customers grow with us" — no expansion path |
| Churn segments | Voluntary vs involuntary; by tier | Aggregate churn hides high-tier churn (the dangerous kind) |
| Power-user features | What turns Joe-the-user into Joe-the-evangelist | Feature set is flat; no power-user lock-in |
| Self-serve admin | Can admin manage seats / billing / SSO themselves | Admin features require support ticket — SMB hates this |
| Integrations | Top 5 named with depth, not "integrations coming" | "We have an API" — but no real integrations |
| Support model | In-app help / docs / chat / email — sized for ARPU | Over-supported SMB at $20/mo = death |
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 · 205 lines · 62 tokens per session scan A 0dbdf942b7a0
b2b-saas-pm-reviewer is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 2,427 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.