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-save)<a href="https://agentmods.dev/commands/vandanaajaydubey111/great-pm/pm-save"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-save/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-save"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-save.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 | $0.00047 | $0.00769 |
| Opus 5.5 | $0.00019 | $0.00308 |
| Sonnet 5.5 | $0.00009 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
pm-save scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 18d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the great-pm /pm-save command. Capture lessons from this session so
the next cycle does not repeat solved problems.
Operating procedure
-
Step 0 — refine the user's query (transparent Mode B). Invoke
query-refiner-pmwith$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/$(date +%Y-%m-%d).log. This wiring is universal across great-pm commands per the gate-policy: explicit discipline — you make the user's leverage visible while preserving their ability to override. -
If the
continuous-learneragent is available (Batch 8), spawn it with the session context and let it do its full job. -
If
continuous-learneris not yet built, extract lessons inline:- What worked? (specific moves the agents/loop got right)
- What did not? (rework, surprises, BLOCKED outcomes)
- Recurring patterns (something seen ≥2 times — worth a lesson)
- Cost outliers (agents that burned unexpectedly much / little)
-
Append to
.great-pm/lessons.mdusing this format (one entry per lesson):## <YYYY-MM-DD> — <one-line lesson title> Context: <what we were doing> Observation: <what happened — concrete, with paths/IDs if relevant> Pattern: <the generalisable rule> Confidence: <low | medium | high> Next time: <what to do differently> -
Check for promotion candidates — any pattern with confidence: high seen ≥3 times across
.great-pm/lessons.md:mkdir -p ~/.great-pm grep -c "^Pattern:" .great-pm/lessons.md 2>/dev/nullIf patterns repeat across initiatives, propose promotion to
~/.great-pm/decisions.md— but never auto-promote. Surface to the human with the proposed entry. -
Update
.great-pm/verdicts/$(date +%Y-%m-%d).logwith the save outcome.
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.
- 18d ago First seen · 76 lines · 47 tokens per session scan A c95543a62d33
pm-save is a command published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 18d ago), licensed MIT. It adds 47 tokens to every session and 769 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
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
scout-work
Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).
attune
AI-powered developer workflows with Socratic discovery.
bulk
Batch API processing with 50% cost savings.
migrate
Use when the user invokes /goal-flight migrate to preview and import existing markdown task lists into Goal Flight draft task-store items.
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.