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 rules/erniker/understudy/understudy-globalgit clone --depth 1 https://github.com/erniker/understudyWhat 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 | $0.00720 | $0.00720 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade C, and why
understudy-global scanned grade C with 1 finding 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 yesterday.
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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Don't interrupt in-progress work to suggest this, and never refuse to keep How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{PROJECT_NAME}} — Project Instructions
Project
- Name: {{PROJECT_NAME}}
- Description: {{PROJECT_DESCRIPTION}}
- Main stack: {{TECH_STACK}}
- Repository: {{REPOSITORY_URL}}
- Project Manager: {{TEAM_LEAD}}
Team context
This project uses the Understudy system: a team of specialized AI agents.
Each agent has a defined role in .cursor/agents/ with detailed instructions.
Available roles are:
- architect — Solution design and architectural decisions
- backend — Implementation of APIs, services and business logic
- frontend — User interfaces and experience
- devops — Infrastructure, CI/CD and operations
- security — Security integrated throughout the entire cycle
- qa-engineer — Testing and software quality
To activate an agent, invoke it from the Agent panel in Cursor.
Spec-Driven Development
This project follows Spec-Driven Development:
- Before writing code, the specification is documented in
docs/spec.md - The spec must be approved by the PM before starting
- Any scope changes are reflected first in the spec
Mandatory context files
| File | Purpose |
|---|---|
docs/spec.md |
Project specification — the source of truth |
docs/decisions.md |
Architectural decision records (ADR) |
docs/session-log.md |
Session log — read at the start of each session |
docs/team-roster.md |
Active team roster and capabilities |
Global rules
At the start of a session
- Always read
docs/session-log.mdto know what was done before - Always read
docs/spec.mdfor project context - Always read
docs/decisions.mdfor decisions already made - Before working, confirm your understanding of the current state
At the end of a session
- Update
docs/session-log.mdwith:- What was done in this session
- What is still pending
- Decisions made
- Blockers identified
Recognizing good stopping points
A long conversation costs more (tokens, time, money) than starting fresh
with a concise summary. Watch for natural stopping points — a feature just
finished with tests passing, a bug fixed and verified, a question fully
answered — and proactively suggest wrapping up: update
docs/session-log.md, then tell the user this is a good point to close
this chat and start a new one, since the next session picks up full context
from docs/session-log.md — nothing is lost.
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.
- yesterday First seen · 89 lines · 720 tokens per session scan C c95ff44a7f92
understudy-global is a cursor rule published in the GitHub repository erniker/understudy (3 stars, last pushed 1mo ago), licensed MIT. It adds 720 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
implementation-workflow
Required plan-first workflow for any implementation request (steps 1–5).
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
nauro-context
Writes durable shared context into Nauro's project store so other agents (a later session or a parallel one) can discover and pull it, finds and reads context another agent left, or captures a resumable brief so your own next session in this environment picks up cleanly. Three modes. Author writes a shared brief for…
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.