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/create-prdnpx skills add ertra/pm-brain-for-cursor --skill create-prdgit 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/create-prd)<a href="https://agentmods.dev/skills/ertra/pm-brain-for-cursor/create-prd"><img src="https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/create-prd.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 | $0.00056 | $0.03680 |
| Opus 5 | $0.00028 | $0.01840 |
| Sonnet 5 | $0.00011 | $0.00736 |
| Haiku 4.5 | $0.00006 | $0.00368 |
Grade A, and why
create-prd 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Writer (pm-brain)
Write the PRD pack — product requirements and success metrics — ideally from an approved product brief (01-product-brief.md in the feature hub or an explicit brief path). Preferred: brief exists → skip Step 0.5 and use the brief as source of truth. If no brief: offer create-product-brief first; if the user wants a PRD anyway, run Step 0.5 (braindump gate per PRODUCT-RULES.md) before Step 1.
Repo convention: Feature hub paths, skipping steps, and the skills table — see 02-templates/README.md (Feature hub convention, Skipping steps, Cursor skills).
The pack is two tightly-coupled files:
02-product-requirements.md— use cases, priorities, cross-surface considerations03-success-metrics.md— business impact, activation, adoption, retention, proposed new events
Step 0: Locate the product brief
- Ask for the PROJECT Jira key (
PROJECT-abcde) or the path to an existing product brief. - Resolve the feature-hub folder:
projects/{PROJECT-KEY}-{slug}/.- If only the key is given, list
projects/and match thePROJECT-{KEY}-*directory. - If multiple match, show them and ask which one.
- If only the key is given, list
- Confirm a brief is available:
01-product-brief.mdin the feature hub, or- An explicit brief path the user provided in Step 0.
If neither exists, suggest
create-product-briefor an external brief path. If they still want a PRD without a brief, continue to Step 0.5 (braindump gate).
Step 0.5: Braindump gate (only when no brief)
Run this step only if neither 01-product-brief.md in the feature hub nor an explicit external brief path is available. If either brief exists, skip Step 0.5 — the brief is the braindump; go to Step 1.
When no brief is available, follow PRODUCT-RULES.md before Step 1:
- Ask 3–5 product-sense questions from
PRODUCT-RULES.md. - Confirm the braindump sufficient? checklist (all four items — see
PRODUCT-RULES.md). - If any item is missing, ask one more targeted question and wait.
- Override: If the user says "skip braindump", proceed to Step 1 and log
braindump: skipped by userin both PRD files' frontmatter when you write them.
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 · 271 lines · 56 tokens per session scan A 974de8ead8f3
create-prd is a skill published in the GitHub repository ertra/pm-brain-for-cursor (22 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 3,680 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…
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.
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…
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…