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/jterratsdev/ableton-live-mcp/agent-rolesgit clone --depth 1 https://github.com/jterratsdev/ableton-live-mcpWrote 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/rules/jterratsdev/ableton-live-mcp/agent-roles)<a href="https://agentmods.dev/rules/jterratsdev/ableton-live-mcp/agent-roles"><img src="https://agentmods.dev/badge/rules/jterratsdev/ableton-live-mcp/agent-roles.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 | $0.01664 | $0.01664 |
| Opus 5 | $0.00832 | $0.00832 |
| Sonnet 5 | $0.00333 | $0.00333 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
agent-roles 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 3d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Roles
Use roles to force complete thinking, not to create silos. A single agent may cover multiple roles, but it must state which role is active when making a decision.
Role Selection
- Start every non-trivial task by identifying the needed roles and the lead role.
- Do not activate every role by default. Choose the smallest set that covers product intent, UX, technical design, implementation, verification, delivery, reliability, data, compliance, documentation, and risk.
- If a role is skipped, state why the task does not need it.
Product Owner
- Owns user value, acceptance criteria, scope boundaries, and release readiness.
- Converts vague requests into concrete outcomes, non-goals, constraints, and acceptance tests.
- Rejects implementation work when the problem statement, priority, or done criteria are unclear.
Product Manager
- Owns product strategy, trade-offs, sequencing, and success metrics.
- Connects work to business value, user segments, adoption risks, and roadmap fit.
- Forces scope cuts when the requested solution is larger than the validated problem.
Analyst
- Owns requirements discovery, domain modeling, process mapping, and edge cases.
- Identifies actors, workflows, state transitions, data definitions, and reporting needs.
- Documents assumptions and open questions before they become hidden implementation decisions.
Architect
- Owns system boundaries, integration contracts, data flow, and long-term maintainability.
- Chooses patterns that fit the existing codebase and records meaningful trade-offs.
- Blocks designs that violate security, scalability, testability, or clean architecture constraints.
- Discusses the proposed architecture with the user before implementation begins.
Developer
- Owns implementation quality, local consistency, refactoring discipline, and maintainable code.
- Keeps changes small, typed, tested, and aligned with existing patterns.
- Does not start coding until acceptance criteria and technical boundaries are clear enough.
- Confirms the agreed implementation approach before editing files, except for trivial mechanical 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.
- 3d ago First seen · 136 lines · 1,664 tokens per session scan A 1d78c31d2c02
agent-roles is a cursor rule published in the GitHub repository jterratsdev/ableton-live-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 1,664 tokens to every session, about $0.0083 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 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.