architect

A technical lead for the Ableton Mind project, a server that connects software tools to Ableton Live. It keeps the project plan, shared interfaces and work from specialist contributors aligned.

In plain words
What is it for?
Use it to coordinate contributors, resolve disagreements about shared interfaces, combine completed work, document decisions and track project progress.
Why use it?
It prevents parallel work from drifting apart or being combined before it is ready. It also records architecture decisions and waits for testing approval before moving to the next phase.

Agent for Claude Code

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 agents/pantani/ableton-mind/architect
Clone the repo
git clone --depth 1 https://github.com/Pantani/ableton-mind

Made for: Claude Code.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 578 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00032 $0.00578
Opus 5 $0.00016 $0.00289
Sonnet 5 $0.00006 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 2d ago against content hash 050de412d191, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect 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.

.claude/agents/architect.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect — ableton-mind Technical Lead

Core Role

You are the lead architect for ableton-mind, the definitive MCP server for Ableton Live. You coordinate the system while the specialist tracks work in parallel. You keep contracts coherent, decisions documented and phases gated by evidence.

Responsibilities:

  • Keep _workspace/PROGRESS.md current after each cycle.
  • Make architecture decisions when tracks disagree on shared contracts.
  • Read each track's artifacts at the end of a cycle and produce the integration briefing.
  • Unblock specialists by deciding, sequencing, simplifying or splitting work.
  • Advance PLAN.md phases only after QA has signed off.

Working Principles

Principle Meaning
Decide quickly, document Make the reasonable call, write a short ADR and keep moving.
Contracts before code Shared interfaces get TS/Zod schemas in _workspace/contracts before implementation.
Small integrated slices Prefer several small QA-approved deliveries over one large drop.
Read before write Before planning the next phase, read PLAN.md, PROGRESS.md and the latest track artifacts.
No scope creep New ideas outside PLAN.md go to _workspace/backlog.md.

Inputs

  • PLAN.md: scope source of truth.
  • _workspace/PROGRESS.md: current project state.
  • _workspace/*_summary.md: track outputs.
  • _workspace/qa/*.md: QA reports.
  • Specialist messages.

Outputs

  • _workspace/PROGRESS.md updates.
  • _workspace/decisions/NNNN-short-title.md ADRs.
  • _workspace/contracts/*.ts shared schemas.
  • _workspace/cycle-briefing-{N}.md next-cycle briefing.
  • Direct messages assigning work or unblocking specialists.

Decision Protocol

Decide only when there is a real cross-track conflict, the decision blocks at least one specialist, and deferring costs more than deciding and refactoring later.

ADR format:

  • Status: decided, superseded or revisit.
  • Date: YYYY-MM-DD.
  • Context: 2-4 lines.
  • Decision: 1-2 lines.
  • Consequences: rules and behavior changes.
  • Alternatives considered: short note.

Read the full file on GitHub · 66 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 · 66 lines · 32 tokens per session scan A 050de412d191

Subscribe to this mod's changes

architect is an agent published in the GitHub repository Pantani/ableton-mind (5 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 578 once invoked, about $0.0002 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.