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.
npx agentmods add commands/phuryn/pm-brain/indexgit clone --depth 1 https://github.com/phuryn/pm-brainWhat 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 | $0.00000 | $0.00526 |
| Opus 5 | $0.00000 | $0.00263 |
| Sonnet 5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
INDEX 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 2d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commands
Operator-facing verbs. Each command is a thin spec: input, files to load, files to update, what to surface. The agent reads the spec, executes against the brain, and reports back per CLAUDE.md § Operating loop.
| Verb | When to run it |
|---|---|
/ingest |
Any new artifact lands — interview, meeting notes, market signal, ad-hoc note |
/prep |
Before a 1:1, exec review, roadmap discussion, or any stakeholder conversation |
/review |
Weekly maintenance sweep (default: Friday) |
/hypothesize |
Generate or refresh hypotheses for a feature (pre-ship across the 5 risk areas, or post-ship from data) |
/decide |
Log a decision: draft the file from the evidence trail, surface for PM sign-off |
/strategy-check |
Drift check between recent decisions / hypotheses / ingestion and knowledge/strategy.md |
/ideate |
A problem needs solution directions grounded in existing evidence and hypotheses |
/risk |
A feature or plan needs the 5-area risk scan; maps to hypothesis hygiene |
/plan |
A new objective lands; turn it into discovery questions, interviews, experiments, hypotheses, decision points |
Conventions
- Every command loads before acting and updates after. No blind drafting.
- Every command ends by surfacing 2-4 bullets per
CLAUDE.md § Operating loop § 7. /prepis read-only at call time. The operator runs/ingestafter the conversation. All other commands draft or update files per autonomy mode.- Commands respect
CLAUDE.md § Operating preferences § Autonomy mode. Underpropose and wait, drafts are presented for approval before saving. - All file paths in each spec are relative to the brain root.
Scope: what these verbs are not
PM Brain is the memory and reasoning layer. PM workflows (JTBD interview structure, Kano analysis, RICE prioritization, opportunity solution trees, experiment design templates) belong in workflow-specific skills, not here. A workflow skill produces an artifact; PM Brain ingests it via /ingest and routes the evidence into durable layers. The split keeps each system thin.
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.
- 2d ago First seen · 28 lines · 0 tokens per session scan A e511deb80dbc
INDEX is a command published in the GitHub repository phuryn/pm-brain (537 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 526 tokens. 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 2026-08-30.
Other commands, from other repositories
obsidian-ingest
Ingest a source into the vault - the vault rewrites itself around new knowledge. Every ingest updates entities, rewrites stale claims, synthesizes new concepts, and resolves contradictions.
create-command
Create a new obsidian-second-brain command via interview - zero markdown editing required.
obsidian-architect
Scan a codebase and write a maintained set of architecture notes into the vault - overview, per-module notes, key decisions. Re-run to refresh without clobbering your edits.
obsidian-visualize
Generate a visual canvas map of your vault - see the shape of your second brain and how knowledge connects.
podcast
Extract metadata, transcript, and summary from a podcast episode, saved as an AI-first note in the vault.
youtube
Extract transcript, metadata, and top comments from a YouTube video - summarized via Gemini (free tier) or Grok and saved to vault. Add --visual to also read the video's frames (scene detection).