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/ertra/pm-brain-for-cursor/startgit clone --depth 1 https://github.com/ertra/pm-brain-for-cursorWhat 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 | $0.00077 |
| Opus 5 | $0.00000 | $0.00039 |
| Sonnet 5 | $0.00000 | $0.00015 |
| Haiku 4.5 | $0.00000 | $0.00008 |
Grade A, and why
start 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 3d 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.
What it actually says
Start — bootstrap company context
The user invoked /start.
Open .cursor/skills/start/SKILL.md and follow it exactly — including First turn — opening message: if name and URL are not both confirmed, use the short one-sentence preamble plus the two input prompts; nothing else.
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.
- 3d ago First seen · 6 lines · 0 tokens per session scan A a6e5bad74dd9
start is a command published in the GitHub repository ertra/pm-brain-for-cursor (22 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 77 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
user-story-gen
Generates INVEST-compliant user stories with acceptance criteria from PRD or feature descriptions.
analytics-scaffold
Generates event tracking code for GA4, Mixpanel, and Amplitude from event specifications.
feature-prioritizer
Prioritizes features using RICE, ICE, MoSCoW, and weighted scoring frameworks with visual output.
roadmap-builder
Generates product roadmaps from prioritized features, team capacity, and strategic goals with Mermaid visualization and Now-Next-Later framework.
release-noter
Generates user-friendly release notes from git commits and PRs with audience-specific tone adjustment (users, team, investors).
git
Git operations with intelligent commit messages and workflow optimization.