the-understudy

the-understudy is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 110 tokens per session (1,123 once invoked), scanned A, original, MIT.

A method for learning how someone makes decisions and writes by studying three to five examples of their real work. It creates a profile, drafts under that profile, and marks the judgments it could not infer.

In plain words
What is it for?
Use it to draft emails, documents, or decisions in your own way. It helps capture what you emphasise, avoid, question, or state cautiously.
Why use it?
Copying surface style can sound like a person without matching their reasoning. Showing the evidence and the gaps makes imitation more accurate and easier to correct.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it to draft emails, documents, or decisions in your own way. It helps capture what you emphasise, avoid, question, or state cautiously.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/the-understudy
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,345 stars · on GitHub · mohitagw15856.github.io

Install

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.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills

Made for: 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 the-understudy

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/the-understudy/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/the-understudy)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/the-understudy"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/the-understudy/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 the-understudy

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/the-understudy"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/the-understudy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,123 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 $0.00110 $0.01123
Opus 5 $0.00055 $0.00562
Sonnet 5 $0.00022 $0.00225
Haiku 4.5 $0.00011 $0.00112

Measured 10d ago against content hash c4e66f44188c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

the-understudy 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 10d 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.

exports/cursor/pm-2027/the-understudy/the-understudy.mdc · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Understudy Skill

"Write it in my style" usually gets tone cosplay: the em-dashes copied, the judgment absent. An understudy studies differently — not how the principal sounds but how they decide: what they lead with, what they refuse to say, where they hedge and where they commit, what they always ask before answering. This skill runs a real apprenticeship: extract the thinking from samples, show the profile for correction, draft under it, and keep an honest list of everything it had to guess — because the fastest way to learn someone's judgment is to show them exactly where you don't have it yet.

What This Skill Produces

  • A thinking profile built from samples: decision patterns, argument structure, commitments and hedges, taboos, signature moves — each with the evidence line it came from
  • An understudy draft of the requested piece, written under that profile
  • The couldn't-infer list: judgment calls the samples didn't cover, with the guess made and the question that would settle it
  • A profile file the user can save and hand back next time (works with the Professional Brain convention)

Required Inputs

Ask for (if not already provided):

  • 3–5 samples of the user's real work — ideally the same genre as the ask (their exec updates to draft an exec update), including at least one they're proud of and, if possible, one with visible edits or a decision they reversed
  • The new piece to draft: audience, situation, what they want to happen
  • Anything the samples predate: new role, new company, changed opinions

Process

  1. Study decisions, not diction. For each sample extract: what it leads with · what it conspicuously omits · where certainty lives vs where hedges live · how bad news is carried · what gets numbers and what gets narrative · the asks it makes and how bluntly. Note tone last.
  2. Write the profile in falsifiable lines. "Leads with the decision, then two reasons, never three" is checkable; "clear and concise" is horoscope. Every line cites its sample. Show the profile and invite corrections — corrections are the highest-value input this skill gets.
  3. Draft under the profile. Apply the decision patterns first, the voice second. Where the new piece demands a judgment the samples never made, make the closest-fit call, mark it inline with ⚠, and add it to the list.
  4. Deliver the couldn't-infer list. Each entry: the gap, the guess made, the one question that would close it. This list shrinking over sessions IS the apprenticeship.
  5. Offer the profile as a file (understudy-profile.md) so the study cost is paid once.

Read the full file on GitHub · 102 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. 10d ago First seen · 102 lines · 110 tokens per session scan A c4e66f44188c

Subscribe to this mod's changes

the-understudy is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,345 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 1,123 once invoked, about $0.0006 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.