pm-brain-for-cursor: Skill for Claude Code

.cursor/skills/critique-agent/SKILL.md

critique-agent is a skill for Claude Code, Cursor from ertra/pm-brain-for-cursor. It costs 69 tokens per session (3,064 once invoked), scanned A, original, MIT.

A review workflow that challenges an existing product brief or PRD, a document describing what a product should do, before it reaches stakeholders.

In plain words
What is it for?
Use it to critique a brief, PRD, metrics pack, or inconsistencies across those documents.
Why use it?
It exposes hidden assumptions, missing information, contradictions, and ways the proposed product could fail.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/.

This is ertra/pm-brain-for-cursor's own configuration. It tells Claude Code and Cursor how to work on pm-brain-for-cursor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pm-brain-for-cursor configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ertra/pm-brain-for-cursor/main/.cursor/skills/critique-agent/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ertra/pm-brain-for-cursor

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for critique-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/critique-agent/github.svg)](https://agentmods.dev/skills/ertra/pm-brain-for-cursor/critique-agent)
Your own site
<a href="https://agentmods.dev/skills/ertra/pm-brain-for-cursor/critique-agent"><img src="https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/critique-agent/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.

agentmods 80×15 button for critique-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/ertra/pm-brain-for-cursor/critique-agent"><img src="https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/critique-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,064 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.03064
Opus 5 $0.00034 $0.01532
Sonnet 5 $0.00014 $0.00613
Haiku 4.5 $0.00007 $0.00306

Measured 9d ago against content hash 3281e67d8da9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

critique-agent 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 9d 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.

.cursor/skills/critique-agent/SKILL.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Critique Agent (pm-brain)

Challenge an existing product brief, PRD, or PRD + metrics pack by surfacing assumptions, gaps, inconsistencies, and likely failure scenarios. You are not killing the idea — you are making it survive the next stakeholder review.

Repo convention: Feature hub paths and stable basenames — see 02-templates/README.md (Feature hub convention). The braindump gate from PRODUCT-RULES.md does not apply here — the doc already exists.

When to Use This Skill

  • Pressure-testing a brief or PRD before sharing with SLT / GM / eng leads
  • A draft "feels too easy" and you want a reality check
  • Preparing for tough questions from skeptical stakeholders (Eng, Finance, Sales, Legal, Design)
  • Sanity-checking brief → PRD → metrics consistency before handoff
  • Pre-mortem: imagine this shipped and failed — why?

What You'll Need

Critical inputs (collect in Step 0 if missing):

  • The doc(s) to critique — PROJECT key + which file(s), or an explicit path
  • Critique mode — brief / prd / pack (PRD + metrics together) / cross-doc (brief vs. PRD vs. metrics consistency)

Nice-to-have inputs:

  • Specific concerns the PM already has ("I'm worried about engineering feasibility on use case 3")
  • Target audience for the upcoming review (SLT vs. eng vs. cross-functional)
  • Calibration: light (top 3 risks) / standard / hard (maximally skeptical)

Step 0: Locate the target doc

  1. Ask for the PROJECT key (PROJECT-abcde) or an explicit file path.
  2. Resolve feature hub: projects/{PROJECT-KEY}-{slug}/. List matching dirs if ambiguous.
  3. Confirm which doc(s) exist and which to critique. Default targets in order of preference:
    • pack (both 02-product-requirements.md + 03-success-metrics.md) if both exist
    • Single doc otherwise
    • cross-doc if 01, 02, and 03 all exist and the user wants consistency checking
  4. Ask the calibration: light / standard / hard. Default = standard.
  5. Ask for any specific concerns the PM already has — they get extra scrutiny.

Read the full file on GitHub · 275 lines

Changes

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.

  1. 9d ago First seen · 275 lines · 69 tokens per session scan A 3281e67d8da9

Subscribe to this mod's changes

critique-agent is a skill published in the GitHub repository ertra/pm-brain-for-cursor (22 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 3,064 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.

Related

Other skills, from other repositories