work-intake-sequencing

work-intake-sequencing is a cursor rule for coding agents from jterratsdev/ableton-live-mcp. It costs 546 tokens per session, scanned A, original, MIT.

A set of rules for turning incoming work into a ready-to-implement GitHub issue and then ordering the implementation. The issue records the goal, acceptance criteria, scope, risks, technical notes, and test expectations.

In plain words
What is it for?
Use it to check issue readiness, refine technical plans, identify affected roles, record assumptions, and sequence changes across models, services, interfaces, and tests.
Why use it?
It prevents coding from starting with incomplete requirements or chat context alone. It also highlights decisions that must be settled before changing behavior, data, security, deployment, or compliance.

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/work-intake-sequencing
Clone the repo
git clone --depth 1 https://github.com/jterratsdev/ableton-live-mcp
Per session 546 This file is loaded in full into every session.
When invoked 546 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 $0.00546 $0.00546
Opus 5 $0.00273 $0.00273
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00055 $0.00055

Measured 2d ago against content hash eb3a83435c01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

work-intake-sequencing 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 2d 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/work-intake-sequencing.mdc · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work Intake & Sequencing

Every work block must start from a refined GitHub issue and follow a safe implementation order. Do not start coding from chat context alone.

GitHub Issue Gate

  • Before starting a work block, confirm the GitHub issue exists and record its issue number.
  • The issue must include user story or job-to-be-done, acceptance criteria, priority, scope, non-goals, technical notes, test expectations, and risk areas.
  • If the issue is missing or vague, create or refine it before implementation.
  • Use the issue number as the Backlog Item ID for commits and PRs.

Technical Refinement

  • Refine the solution with expected files/modules, domain model changes, service/integration changes, controller/CLI/API changes, data flow, failure modes, and test plan.
  • Identify impacted roles before coding: Architect, Developer, QA, Security, DevOps, SRE, DBA, UX/UI, Compliance/Privacy, Technical Writer, or Game Designer.
  • Record assumptions and open questions. Block implementation when a decision affects user behavior, data contracts, security, deployment, or compliance.

Implementation Order

  • Start with models and domain: types, schemas, entities, value objects, invariants, and validation.
  • Then implement service and integration layer: orchestration, repositories, adapters, provider interfaces, external APIs, and side effects.
  • Then implement controllers and entry points: CLI commands, API routes, UI handlers, jobs, and web controllers.
  • Finally wire evidence: unit tests, integration tests, Playwright or smoke tests, static analysis, docs, and handoff.

Security Review Trigger

  • Run a security review when work touches auth, authorization, identity, secrets, PII, payments, file paths, shell/process execution, network calls, dependency changes, encryption, TLS, cookies, sessions, CORS, webhooks, or infrastructure.
  • Production networked services must consider TLS 1.2+, certificate management, HSTS where applicable, secure cookies, least privilege, and secret rotation.
  • If security is out of scope, state why. If uncertain, involve Security before implementation.

Read the full file on GitHub · 40 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. 2d ago First seen · 40 lines · 546 tokens per session scan A eb3a83435c01

Subscribe to this mod's changes

work-intake-sequencing is a cursor rule published in the GitHub repository jterratsdev/ableton-live-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 546 tokens to every session, about $0.0027 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.