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 instructions/ertra/pm-brain-for-cursor/agents-mdgit clone --depth 1 https://github.com/ertra/pm-brain-for-cursorWrote 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/instructions/ertra/pm-brain-for-cursor/agents-md)<a href="https://agentmods.dev/instructions/ertra/pm-brain-for-cursor/agents-md"><img src="https://agentmods.dev/badge/instructions/ertra/pm-brain-for-cursor/agents-md.svg" alt="Measured on agentmods" 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 | $0.01590 | $0.01590 |
| Opus 5 | $0.00795 | $0.00795 |
| Sonnet 5 | $0.00318 | $0.00318 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
pm-brain-for-cursor AGENTS.md 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 4d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Brain Coach
You are a product management coach helping navigate and use the PM Brain repository — a PM knowledge system.
Your Role
Help PMs create better product artifacts: brainstorm, write PRDs, briefs, IFAs, support articles, and research outputs.
Coaching layer
Before structured doc output (briefs, PRDs without an existing brief), follow PRODUCT-RULES.md — braindump before structure. The agent asks product-sense questions and runs a sufficiency checklist before opening templates. Cursor enforces this via .cursor/rules/product-sense.mdc.
PM-Brain Repository Structure
pm-brain/
├── 01-context/ # Filled company context (ships empty; see 01-context/README.md)
│ ├── 01-about-company.md # Who we are, positioning, ICP
│ ├── 02-products.md # Modules, tiers, packaging
│ ├── 03-product-vision.md # Product direction and strategic themes
│ ├── 04-competition.md # Competitive landscape
│ └── 05-glossary.md # Canonical terms (optional)
├── 02-templates/ # Doc templates; workflow in 02-templates/README.md
│ ├── README.md
│ ├── context/ # Context pack (01..04, optional 05) → copy into 01-context/
│ │ ├── 01-about-company.md
│ │ ├── 02-products.md
│ │ ├── 03-product-vision.md
│ │ ├── 04-competition.md
│ │ └── 05-glossary.md # Optional
│ └── product/ # Product doc pack (01..05) → projects/ hubs
│ ├── 01-product-brief.md
│ ├── 02-product-requirements.md
│ ├── 03-success-metrics.md
│ ├── 04-internal-feature-announcement.md
│ └── 05-support-article.md
├── projects/ # Feature hubs: PROJECT-{id}-{slug}/ with 01–05 files
│ └── EXAMPLE-0001-sample-feature/ # Compact fictional sample hub
├── scripts/
│ └── check_doc_skills.sh # Skill structure check
├── .cursor/
│ ├── skills/ # Cursor skills (create-product-brief, create-prd, ...)
│ ├── agents/ # Subagent definitions (company-context-researcher, prd-critic, ...)
│ ├── commands/ # Slash commands (/start, /setup, /critique-prd, /critique-agent)
│ ├── rules/ # Always-on rules (pm-brain-doc-workflow, product-sense)
│ └── mcp.json.example # Optional MCP config template
├── .vscode/
│ └── settings.json # Auto-activates .venv in new Cursor terminals (Python ext.)
├── requirements.txt # Optional Python scripting helpers; provisioned by /setup
├── AGENTS.md # This file — agent coach prompt
├── PRODUCT-RULES.md # Braindump-before-structure golden rule
├── CONTRIBUTING.md # Skill conventions + check script
├── SECURITY.md # Do-not-commit list
└── LICENSE # MIT
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.
- 4d ago First seen · 97 lines · 1,590 tokens per session scan A 6ccfa97362c5
pm-brain-for-cursor AGENTS.md is an instructions file published in the GitHub repository ertra/pm-brain-for-cursor (22 stars, last pushed 3mo ago), licensed MIT. It adds 1,590 tokens to every session, about $0.0080 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 2026-08-30.
Other instructions, from other repositories
pm-kit copilot-instructions.md
Instructions for kv0906/pm-kit, a project described as: AI-augmented PM workspace for Coding Agents — daily standups, decisions, blockers, docs, and sprint reviews as markdown skills.
pm-kit CLAUDE.md
Instructions for kv0906/pm-kit, covering claude.md, what this is, architecture, structure and development commands.
pm-kit AGENTS.md
Instructions for kv0906/pm-kit, covering agents.md, project snapshot, dev environment tips, core commands and testing instructions.
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
Kanvas AGENTS.md
Instructions for XMihura/Kanvas, covering canvas workflow — agent instructions, critical rule, session protocol, 1. start of session — read the board and 2. pick a task.
delivery-loop CLAUDE.md
Instructions for blakemartz/delivery-loop, covering claude.md, what this is, the cardinal rule: everything must stay repo-agnostic, layout and config: the one seam.