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 skills/ertra/pm-brain-for-cursor/startnpx skills add ertra/pm-brain-for-cursor --skill startgit 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.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 | $0.00050 | $0.02397 |
| Opus 5 | $0.00025 | $0.01198 |
| Sonnet 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 5d 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.
- 5d 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 3mo ago), licensed MIT. It adds 50 tokens to every session and 2,397 once invoked, about $0.0003 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 skills, from other repositories
jira
Jira integration via acli CLI. Use when user says '/jira', 'check Jira board', 'create Jira ticket', 'move ticket to done', 'search Jira', 'sync blockers from Jira', 'what's in the sprint', 'Jira status', 'assign ticket', 'view backlog', or wants to interact with Jira issues, sprints, or boards from the terminal.
notion
Bridge PM-Kit vault with Notion workspace — search, sync, publish, and link vault notes to Notion pages. Use when the user says "/notion", "notion sync", "publish to notion", "notion search", "sync from notion", "push to notion", "notion setup", mentions Notion in any project management context, wants to share vault…
excalidraw-generator
Professional Excalidraw diagram generation expert that creates complete, valid .excalidraw.json files based on user descriptions. Use ONLY when users explicitly mention "Excalidraw" or request to create diagrams specifically with Excalidraw (e.g., "用 Excalidraw 画个流程图", "generate an Excalidraw diagram", "create…
onboard
Interactive onboarding — sets up your first project, learns who you are, generates core/identity.md profile, creates your first daily note, then loads vault context. For returning users, skips setup and loads context directly.
linear
Interact with Linear for issue tracking — search, create, sync, and link issues to vault notes. Use when the user says "/linear", "linear issues", "sync linear", "create issue", "link to linear", "check linear", "what's assigned to me", "my linear tasks", mentions Linear in any project management context, or wants to…
obsidian-cli
Control Obsidian from the terminal using the obsidian CLI. Use when the agent needs to open notes, search the vault inside Obsidian, append/prepend content to the active file, create notes from templates, manage properties, check backlinks/orphans, query Bases, or interact with the running Obsidian app. Requires…