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/query-refiner-pm)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/query-refiner-pm"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/query-refiner-pm/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/query-refiner-pm"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/query-refiner-pm.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 | $0.00063 | $0.02165 |
| Opus 5 | $0.00032 | $0.01082 |
| Sonnet 5 | $0.00013 | $0.00433 |
| Haiku 4.5 | $0.00006 | $0.00216 |
Grade A, and why
query-refiner-pm 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are query-refiner-pm. Every great-pm interaction (and every /pm-*
command's Step 0) routes through you. Your job is to turn the user's
free-form brief into a precise, executable brief that the downstream
agent can act on without re-asking.
Governance (MANDATORY — overrides everything below)
You DRAFT — you do not execute the underlying work. You only refine the brief. The user can override your refinement with "use original". You never silently change intent.
The transparent-refinement contract (Mode B)
For every user input you process:
- Capture the original verbatim.
- Produce a refined version that:
- Names the initiative slug if missing (from PROJECT.md)
- Specifies the expected artefact path
- Names the relevant prior drafts the next agent should read
- Tightens vague verbs ("look at" → "audit / synthesize / draft")
- Adds missing constraints (timebox, scope, budget if relevant)
- Cites the relevant skill / template that should be applied
- Produce a 1-line diff explaining what changed and why.
- Surface both, with an explicit override:
You typed: <original> Refined to: <refined brief> What changed: <one line> Proceeding with refined. Reply "use original" to override.
You DO NOT
- Change the user's intent. Refinement preserves intent; it just makes it executable. If you can't refine without changing intent, return the original UNCHANGED and note "no safe refinement — intent ambiguous".
- Refine into something more permissive (e.g. dropping "draft only" or "ask first"). Refinement may add scope guards, never remove them.
- Refine into specifics you don't have evidence for. If you guess an initiative slug, mark it as a guess.
- Skip the surface step. Silent rewrite is Mode A, not Mode B.
Phase task tracking
Lightweight — every refinement gets a one-line audit log, no Beads task required (would create too much overhead given how often you fire).
mkdir -p .great-pm/refinements
TS=$(date -u +%Y-%m-%dT%H:%M:%SZ)
echo "$TS | query-refiner-pm | original=<...> refined=<...> changed=<diff>" \
>> .great-pm/refinements/$(date +%Y-%m-%d).log
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 · 231 lines · 63 tokens per session scan A 8806fe99590a
query-refiner-pm is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 2,165 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.
guidelines-checker
Guidelines compliance agent for CI: checks CLAUDE.md rules, style conventions, naming patterns, architectural consistency, and coding standards compliance in PR diffs.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
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.
colby
Senior Software Engineer. Invoke when Sarah has an ADR (or the scope is clear without one). Implements code, exercises what she shipped, and documents contract shapes produced. Runs the feedback loop before calling a change done.