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-experiment)<a href="https://agentmods.dev/commands/vandanaajaydubey111/great-pm/pm-experiment"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-experiment/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-experiment"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-experiment.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 | $0.00042 | $0.00923 |
| Opus 5.5 | $0.00017 | $0.00369 |
| Sonnet 5.5 | $0.00008 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
pm-experiment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the great-pm /pm-experiment command. Author a pre-registered
experiment.
Parse arguments
<hypothesis-slug>(required) → kebab-case slug (e.g.onboarding-shorter-flow).--type=(optional, experiment-designer recommends if omitted).ab— classic two-arm A/B.multivariate— multiple factors.holdout— one cohort doesn't get the change (for long-term effects).switchback— time-sliced (for marketplace / two-sided experiments).
Pre-flight
SLUG="${1:?usage: /pm-experiment <hypothesis-slug> [--type=...]}"
mkdir -p .great-pm/drafts
ls .great-pm/drafts/metrics-plan-*.md 2>/dev/null && echo "METRICS_EXISTS" || echo "NO_METRICS"
If NO_METRICS → WARN. Experiments without a pre-defined metrics plan
are HARKing (Hypothesising After Results Known). Recommend running
/pm-metrics first.
Operating procedure
-
Step 0 — refine the user's query (transparent Mode B). Invoke
query-refiner-pmwith$ARGUMENTS. The refiner returns:You typed: <original> Refined to: <refined brief> What changed: <one line> Proceeding with refined. Reply "use original" to override.Use the refined version as the brief for subsequent steps UNLESS the user replies "use original". Log the refinement to
.great-pm/refinements/$(date +%Y-%m-%d).log. This wiring is universal across great-pm commands per the gate-policy: explicit discipline — you make the user's leverage visible while preserving their ability to override. -
experiment-designer
- Brief: author the experiment doc with:
- Hypothesis (one sentence with mechanism) — "If we X, then Y will move by Z because mechanism." If the mechanism is hand-wavy, the result won't generalise.
- Primary metric (must be pre-defined in metrics plan).
- MDE (minimum detectable effect).
- Guardrail metrics (latency, errors, long-term retention).
- Test design (type + justification + sample size + power + alpha).
- Pre-registered stopping rules (no peeking before planned end).
- Risks (novelty effect, seasonality, network effects).
- Empty read-out section (DO NOT pre-fill).
- Output:
.great-pm/drafts/experiment-<slug>.mdusingtemplates/EXPERIMENT-template.md.
- Brief: author the experiment doc with:
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 · 89 lines · 0 tokens per session scan A 3a60c5e13328
pm-experiment is a command published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 923 once invoked, about $0.0002 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.