Borrowing it
Nothing to install: this file belongs to ertra/pm-brain-for-cursor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ertra/pm-brain-for-cursor/main/.cursor/skills/start/SKILL.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/skills/ertra/pm-brain-for-cursor/start)<a href="https://agentmods.dev/skills/ertra/pm-brain-for-cursor/start"><img src="https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/start/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/skills/ertra/pm-brain-for-cursor/start"><img src="https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/start.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 | $0.00050 | $0.02397 |
| Opus 5.5 | $0.00020 | $0.00959 |
| Sonnet 5.5 | $0.00010 | $0.00479 |
| Haiku 4.5 | $0.00005 | $0.00240 |
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 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start — Company context bootstrap
Collect company name and website URL, research the public web, then populate 01-context/ from 02-templates/context/. Braindump gate does not apply.
First turn — opening message (strict)
When /start is invoked and both company name and website URL are not already confirmed in the user's message:
- Use a one-sentence preamble only, then the two input prompts. No greeting, skill overview, step list, links, or extra explanation.
- Do not mention research, subagents, templates, or next steps until inputs are confirmed.
Allowed opening (keep this shape; wording may vary slightly):
I'll fill
01-context/for you — I just need two pieces of info:Company name — display name for your company
Website URL — homepage (e.g.https://example.com)
Use AskQuestion when available with the same preamble plus exactly those two fields; otherwise post the preamble and two prompts in chat.
If the user already provided name or URL in the invoke message, use the same one-sentence preamble and ask only for the missing field.
Step 0 — Collect inputs (strict)
Before any web fetch or file write, obtain and confirm:
- Company name (display name)
- Website URL (homepage)
If the user invoked /start with name or URL in the message, confirm both values before proceeding — still without extra explanatory text until both are set.
Normalize URL:
- Ensure scheme:
https://(upgradehttp://if needed) - Strip trailing slash from path (keep path if not homepage)
- Reject obviously invalid URLs (no domain)
Do not fetch the web, spawn research, or write files until both values are confirmed.
Step 1 — Spawn company-context-researcher
Do not research inline in the main context when a subagent is available — isolated research reduces hallucination and keeps the orchestrator focused on template mapping.
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 · 162 lines · 50 tokens per session scan A ee6498efb0e5
start is a skill published in the GitHub repository ertra/pm-brain-for-cursor (22 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 2,397 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 2026-08-30.
Other skills, from other repositories
replit-deck
For product and technical management work: turn PRDs, roadmaps, RFCs, architecture reviews, and retros into decision documents. Built around the core query "pm-feature-business-case-deck", with product strategy lead judgment, buyer-ready proof, and this outcome: approve the feature, architecture, roadmap, or incident…
hps-true-blueprint
OpenDesign's engineering blueprint: how the sandbox, sidecar, and daemon fit — the system diagram and the invariants. Built as a decision-grade product management deck for engineering org.
design-critique
Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.
analytics-product
Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.
deck-open-slide-canvas
OpenDesign's architecture review: the local daemon + agent-runtime design, the tradeoffs, and the decision to lock. Built as a decision-grade product management deck for staff eng, tech leads, security.
mockup-device-3d
Static iPhone and MacBook 3D-style showcase with real HTML embedded on screens, glass-lens refraction, and 360-degree turntable composition.