Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add VandanaAjayDubey111/great-pm/plugin install 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/grill-me)<a href="https://agentmods.dev/commands/vandanaajaydubey111/great-pm/grill-me"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/grill-me/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/grill-me"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/grill-me.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 | $0.00094 | $0.00936 |
| Opus 5.5 | $0.00038 | $0.00374 |
| Sonnet 5.5 | $0.00019 | $0.00187 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
grill-me 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the great-pm /grill-me command. Embody the grill-me agent
(read ${CLAUDE_PLUGIN_ROOT}/agents/grill-me.md and follow it exactly) and
run the interrogation inline, in this conversation — grill-me is a
multi-turn conversation with the human and MUST NOT be spawned as a
subagent from here (a subagent cannot hear the human's answers).
Pre-flight
echo "cwd=$(pwd)"
ls .great-pm/PROJECT.md 2>/dev/null && echo "PROJECT_OK" || echo "NO_PROJECT"
NO_PROJECT→ still proceed (a grill is exactly what you do before a project exists), but note in the brief that PROJECT.md is missing and include the copy-template step in the recommended next step.- If
$ARGUMENTSis empty → ask for the idea in one line and wait. That's the only pre-question allowed.
Step 0 — deliberately NO query-refiner (documented exception)
Unlike other great-pm commands, do NOT run query-refiner-pm here.
Reason (do not "fix" this): grill-me's Round 1 does the refinement job
conversationally, and the interrogation needs the human's RAW framing —
angle 5 (reframe) and angle 8 (the unspoken) work on how the human
naturally posed the idea. Refining first would launder exactly the
assumptions the grill exists to surface.
Operating procedure
- Take
$ARGUMENTSverbatim as the raw framing. Build a kebab-case slug from the first 2–4 meaningful nouns. - Run grill-me's INLINE procedure end-to-end: context absorb → Round 1 (wide) → mirror → Rounds 2–3 (adaptive, stop conditions apply) → synthesize → file unknowns (two-part blocker test) → hand off.
- Write the brief to
.great-pm/discover/situation-<slug>.md. - Close with grill-me's DONE line + the hand-off offer:
"Run
/pm-startwith this sharpened brief?" If the human says yes, invoke/pm-startwith the sharpened problem statement (never auto-start without the yes).
Reporting
Use grill-me's reporting contract verbatim (DONE/BLOCKED, brain append, verdict log). The situation brief is the artifact of record.
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 · 72 lines · 94 tokens per session scan A 976766d43788
grill-me is a command published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 936 once invoked, about $0.0004 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.