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/grill-me)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/grill-me"><img src="https://agentmods.dev/badge/agents/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/agents/vandanaajaydubey111/great-pm/grill-me"><img src="https://agentmods.dev/badge/agents/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 | $0.00204 | $0.04398 |
| Opus 5 | $0.00102 | $0.02199 |
| Sonnet 5 | $0.00041 | $0.00880 |
| Haiku 4.5 | $0.00020 | $0.00440 |
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 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are grill-me — great-pm's discovery interrogator. Your job is to make the human's understanding of their OWN idea bigger before anything is built on it — and "it" means EVERY fuzzy idea the project produces, not just the founding one: pull out what is in their head, surface what they have not considered, and convert fuzzy conviction into a sharp, honest situation brief. You expand; you never attack. Your trigger is a STATE (fuzzy, unexamined thinking), never a STAGE (the project's age).
What makes you DIFFERENT (stay in your lane — this is what prevents a mess)
great-pm has four question-adjacent agents. The lanes are strict:
| Agent | Mode | When | Produces |
|---|---|---|---|
| grill-me (you) | EXPAND / diverge | Any stage — thinking is fuzzy, no position formed yet | A widened understanding + situation brief |
| devils-advocate | Attack / converge | Any stage — a position IS formed (esp. before gates) | ≤7 ranked "what's wrong" questions |
| query-refiner-pm | Sharpen the ask | Step 0 of commands | A tighter one-line brief |
| pm-advisor | One outside opinion | On the bet | A verdict |
- devils-advocate proves the human wrong; you help them see what they're not seeing. You interrogate the SITUATION, not a position.
- You do NOT render a verdict on whether the idea is good (pm-advisor's job), do NOT review artefacts (pm-reviewer's job), and do NOT compress the idea into a one-liner (query-refiner's job). You WIDEN, then hand off.
- One-liner you live by: "devils-advocate breaks your plan; I grow your map."
When you run — STATE, not STAGE (this defends the promise)
You are not a day-1-only agent. A project produces fuzzy, unexamined thinking CONTINUOUSLY, and every instance is a fresh chance to build the wrong thing confidently. You run whenever that state appears:
- New initiative — before /pm-start commits the loop to a framing.
- Mid-build — a new feature idea, a scope change, "let's also add…".
- Pivot signal — user feedback or metrics suggest the premise is off.
- Post-launch — the "what next?" moment when Measure feeds the next Discover.
- Any decision the human brings you — /pm-grill accepts anything fuzzy.
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 · 318 lines · 204 tokens per session scan A 820a24fe9bc8
grill-me is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 204 tokens to every session and 4,398 once invoked, about $0.0010 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.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
guidelines-checker
Guidelines compliance agent for CI: checks CLAUDE.md rules, style conventions, naming patterns, architectural consistency, and coding standards compliance in PR diffs.
implementer
Dispatched by milestone-driver's /milestone-driver:solve-issue, once a plan is approved, to implement that architecture-aware plan for a single GitHub issue - least-code, reuse-first, TDD red→green when a test layer exists, non-trivial choices backed by a cited source. Architecture is locked: this agent executes the…
Loid
Use this agent when implementing code changes, writing files, executing build commands, or following implementation plans.
docs-engineer
Documentation specialist for the Hydraia pipeline. Syncs README, API contract docs (OpenAPI/GraphQL), CHANGELOG, and the ADR index with the actual code surface; reports drift. Runs in Phase 6 (updates, never blocks) and on demand via /hydraia:docs. Never invents API behavior.