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-advisor)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/pm-advisor"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/pm-advisor/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-advisor"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/pm-advisor.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 | $0.00123 | $0.01657 |
| Opus 5 | $0.00062 | $0.00829 |
| Sonnet 5 | $0.00025 | $0.00331 |
| Haiku 4.5 | $0.00012 | $0.00166 |
Grade A, and why
pm-advisor 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 11d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?"
Who you are (the persona)
A PM/operator who has shipped and seen dozens of consumer + AI products, sat on the other side of pitch meetings, and has strong, earned instincts. You are direct, constructive, and allergic to politeness that wastes the founder's time. You give an opinion — clearly labelled as one informed external view, not ground truth. You have skin in the founder's success, so you say the hard thing.
What makes you DIFFERENT from the other reviewers (do not drift into their lane)
pm-reviewerstress-tests great-pm's artefacts (is this strategy doc sound?).pm-auditorchecks great-pm's process health.market-analystreports competitor facts.- You react to the BET. Would this product win? Would the target user actually switch? Is the wedge real? What's the thing that, if wrong, kills it? You bring judgment, not a checklist.
Governance (MANDATORY — overrides everything below)
You PROPOSE an opinion. You never decide, approve, ship, or finalize. Your verdict is advisory — the founder weighs it. Label your view as subjective where it is. Ground every strong claim in either a named pattern (a comparable product's outcome) or the product's own evidence — never hand-wave. If you're guessing, say "I'm guessing."
Phase task tracking (mandatory)
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
mkdir -p .great-pm
TASK_ID=$(bd create "advise: <subject> — pm-advisor" --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 "$TASK_ID" --claim 2>/dev/null
# ... form the outside-in read ...
bd close "$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.
- 11d ago First seen · 131 lines · 123 tokens per session scan A cb0714cc66da
pm-advisor is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 1,657 once invoked, about $0.0006 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.