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-crystallize)<a href="https://agentmods.dev/commands/vandanaajaydubey111/great-pm/pm-crystallize"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-crystallize/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-crystallize"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-crystallize.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 | $0.00048 | $0.00801 |
| Opus 5.5 | $0.00019 | $0.00320 |
| Sonnet 5.5 | $0.00010 | $0.00160 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
pm-crystallize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the great-pm /pm-crystallize command. Promote a battle-tested lesson to cross-project memory.
Governance reminder
You PROPOSE; the human DECIDES. Never write to ~/.great-pm/decisions.md without explicit human approval in this turn.
Operating procedure
-
Step 0 — refine the user's query (transparent Mode B). Invoke
query-refiner-pmwith$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. -
Identify candidates:
- If
$ARGUMENTSempty orauto→ spawncontinuous-learnerto scan all of.great-pm/lessons.mdfor entries withHits: 3(or higher) ANDConfidence: high. - If
$ARGUMENTSis a lesson slug → locate that specific entry.
- If
-
For each candidate, build a proposal:
Promotion proposal — <slug> Source lessons (N entries in .great-pm/lessons.md): - <YYYY-MM-DD>: <title> - ... Recommended cross-project rule (one line): <rule> Applies to archetypes: <list — e.g. b2b-saas, consumer-app, all> Status: PENDING HUMAN APPROVAL -
Present the proposals to the human and STOP. Wait for an explicit "yes promote " or "promote all" before writing.
-
On approval for a specific slug:
- Append the proposal text +
Crystallized: <YYYY-MM-DD>to~/.great-pm/decisions.md. - Mark the source entries in
.great-pm/lessons.mdwithPromoted: yes(Edit; not rewrite).
- Append the proposal text +
Output shape
Crystallization candidates (Hits ≥3, Confidence: high)
[1] <slug>
Sources: <N> lessons (<dates>)
Rule: <one-line>
Applies-to: <archetype(s)>
[2] <slug>
...
To promote: say "promote <slug>" or "promote all".
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 · 85 lines · 48 tokens per session scan A ea606fbf6137
pm-crystallize is a command published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 801 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 2026-08-31.
Other commands, from other repositories
build-corpus
Use when the user invokes /goal-flight build-corpus to build or refresh the private Goal Flight dispatch-context corpus.
remember
Store, retrieve, search, and manage persistent memory across sessions.
rekindle
Recover a fellowship after a session crash. Scans worktrees and quest state, presents a recovery dashboard, and re-spawns Gandalf with recovered quest context. Use when returning to a crashed or expired fellowship session.
config
View and toggle LORE stages (inject, index, review, beliefs, skills, streaming).
wiki
Run the LLM Wiki — initialize, ingest, curate, or query. The plugin probes vault state and chooses the right next step.
approve
Review and approve one exact staged LORE proposal.