agent-roles

agent-roles is a cursor rule for coding agents from jterratsdev/ableton-live-mcp. It costs 1,664 tokens per session, scanned A, original, MIT.

A set of software-delivery roles that clarify who is responsible for product goals, requirements, design, implementation, testing, delivery, reliability, and risk.

In plain words
What is it for?
Use it to choose the right responsibilities for a non-trivial task, assign a lead role, identify missing work, and explain why certain roles are not needed.
Why use it?
It prevents important parts of a task from being overlooked and turns vague requests into clear outcomes, constraints, and acceptance checks.

Cursor rule

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.

agentmods
npx agentmods add rules/jterratsdev/ableton-live-mcp/agent-roles
Clone the repo
git clone --depth 1 https://github.com/jterratsdev/ableton-live-mcp

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 agent-roles

README.md
[![agentmods](https://agentmods.dev/badge/rules/jterratsdev/ableton-live-mcp/agent-roles.svg)](https://agentmods.dev/rules/jterratsdev/ableton-live-mcp/agent-roles)
Your own site
<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>
Per session 1,664 This file is loaded in full into every session.
When invoked 1,664 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01664 $0.01664
Opus 5 $0.00832 $0.00832
Sonnet 5 $0.00333 $0.00333
Haiku 4.5 $0.00166 $0.00166

Measured 3d ago against content hash 1d78c31d2c02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

rules/agent-roles.mdc · 136 lines

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.

Read the full file on GitHub · 136 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. 3d ago First seen · 136 lines · 1,664 tokens per session scan A 1d78c31d2c02

Subscribe to this mod's changes

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.