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/commands/vandanaajaydubey111/great-pm/pm-inbox)<a href="https://agentmods.dev/commands/vandanaajaydubey111/great-pm/pm-inbox"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-inbox/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/commands/vandanaajaydubey111/great-pm/pm-inbox"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-inbox.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 | $0.00034 | $0.00677 |
| Opus 5.5 | $0.00014 | $0.00271 |
| Sonnet 5.5 | $0.00007 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
pm-inbox 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 1mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the great-pm /pm-inbox command. Surface every decision waiting on
the human.
Operating procedure
-
Open decisions FIRST (anti-drift). Before gates, surface every unanswered decision so none is lost to scroll:
bd list --label open-decision --status open 2>/dev/nullShow P0 (blocking — a gate cannot pass) above P2 (advisory). For each: the question, what it blocks, and the default-if-unanswered. These are the things the loop is waiting on you for — they head the inbox.
-
List open gates from Beads:
bd list --label gate --status open 2>/dev/null -
For each open gate, locate the associated decision package:
- gate:strategy →
.great-pm/drafts/product-strategy-*.md+roadmap-*.md+ pm-reviewer verdict at.great-pm/reviews/ - gate:spec →
.great-pm/drafts/prd-*.md+ spec-reviewer verdict + metrics plan - gate:launch →
.great-pm/drafts/launch-plan-*.md+gtm-plan-*.md+ pm-reviewer verdict
- gate:strategy →
-
For each, show:
<gate-id> | <initiative> | <gate-type> | pm-reviewer verdict: <STRONG|NEEDS-WORK|WEAK> Recommendation: <one line from the package> Risks: <one line> Open questions for you: <list> See: <path to draft + reviewer verdict> -
List any BLOCKED agents from
.great-pm/verdicts/$(date +%Y-%m-%d).log:grep BLOCKED .great-pm/verdicts/*.log 2>/dev/null | tail -10 -
List any P0 items from Beads:
bd list --priority 0 --status open 2>/dev/null
Reporting
- DONE:
DONE: inbox — <N> gates pending, <M> blocked agents, <K> P0 items.If all zero:DONE: inbox clear — no decisions pending. - BLOCKED: only if Beads itself is unreachable AND the
.great-pm/tasks.mdfallback is also missing.
Notes
- pm-reviewer's verdict on each gate package travels here unedited — the human sees STRONG / NEEDS-WORK / WEAK exactly as pm-reviewer wrote it.
- Always-on agents (feedback-synthesizer, market-analyst, skill-scout) do not produce gates, but their recurring findings may surface as P1/P2 items.
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.
- 1mo ago First seen · 64 lines · 34 tokens per session scan A 723733a4f6ed
pm-inbox is a command published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 677 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-21.
Other commands, from other repositories
poc
Before building on an unproven idea, get a timeboxed yes/no answer — start a hypothesis-driven POC that skips 80% of the production pipeline and forces ship/pivot/kill at expiry, then promote a shipped POC through the audits it skipped.
rfc
RFC process for cross-team decisions. Create, track, and close RFCs. Accepted RFCs auto-create ADRs.
exception
Signed gate-exception registry — replace ad-hoc --admin / --no-verify bypasses with an auditable, signed, expiring record (who · why · gate · scope · expiry). Create / list / check exceptions.
new-track
Create a new development track with spec, plan, and metadata.
conductor-new-track
Create a new development track with spec, plan, and metadata.
dashboard
Starts the live web dashboard for the current fellowship — quest/scout progress, gate approvals, and event history — in the background, and prints the URL.