ai-maestro-architect-agent: Instructions file for Claude Code

CLAUDE.md

ai-maestro-architect-agent CLAUDE.md is an instructions file for Claude Code from Emasoft/ai-maestro-architect-agent. It costs 947 tokens per session, scanned A, original, MIT.

A Claude Code instruction file for the AI Maestro architect role. It defines project guidance for architecture work and explains how the role uses shared memory across projects.

In plain words
What is it for?
Use it to guide architecture tasks, requirements analysis, API research, implementation handoffs, and recall or updating of project knowledge.
Why use it?
It keeps the architect agent's behavior and memory handling consistent, including where private, project, and user-level notes belong.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_DATA} variable. Also seen: reads .claude/ paths; mentions subagents.

This is Emasoft/ai-maestro-architect-agent's own configuration. It tells Claude Code how to work on ai-maestro-architect-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-maestro-architect-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Emasoft/ai-maestro-architect-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Emasoft/ai-maestro-architect-agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Emasoft/ai-maestro-architect-agent

Made for: Claude Code.

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 ai-maestro-architect-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/emasoft/ai-maestro-architect-agent/claude-md/github.svg)](https://agentmods.dev/instructions/emasoft/ai-maestro-architect-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/emasoft/ai-maestro-architect-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/emasoft/ai-maestro-architect-agent/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-maestro-architect-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/emasoft/ai-maestro-architect-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/emasoft/ai-maestro-architect-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 947 This file is loaded in full into every session.
When invoked 947 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00947 $0.00947
Opus 5 $0.00474 $0.00474
Sonnet 5 $0.00189 $0.00189
Haiku 4.5 $0.00095 $0.00095

Measured 8d ago against content hash 3a895e8b471b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ai-maestro-architect-agent CLAUDE.md 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 8d 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.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ai-maestro-architect-agent (AMAA) — project instructions

AMAA is the ARCHITECT role plugin of the AI Maestro fleet: one architect per project, owning technical architecture design, requirements analysis, API research, and complete implementation handoffs.

Memory — use the GLOBAL janitor-hosted system (proactively)

AMAA uses the global, user-level janitor memory system — NOT a per-plugin one. The skills are /janitor-memory-recall · /janitor-memory-write · /janitor-memory-update; the protocol + recall law (index by the SYMPTOM, never the answer's jargon) live in ~/.claude/rules/markdown-memory-recall.md (the janitor installs that rule every session). Three scopes:

  • LOCAL ~/.claude/projects/<slug>/memory/ — machine-private notes (harness; paths, hostnames, hints).
  • PROJECT <repo>/.claude/project/memory/ — git-tracked + pushed, shared by every contributor (no secrets).
  • USER ${CLAUDE_PLUGIN_DATA}/memory/ — the janitor's fixed plugin-data dir; cross-project knowledge.

AMAA ships no per-plugin memory skills — it relies solely on the janitor's global ones. (Distinct from amaa-session-memory, which restores transcript/session context — a separate concern.)

The proactive-use contract (applies to the main agent AND every sub-agent it spawns)

  • RECALL BEFORE ACTING — before authoring a TRDD, making a design decision, re-researching an API, recommending a candidate, or debugging a recurring problem, run /janitor-memory-recall first, indexed by the symptom (the user's words / the design question), across all 3 scopes. Unprompted. "Have we hit this before? did the user already state a preference?"
  • WRITE / UPDATE AFTER SOLVING — after a non-trivial decision or solved problem, capture it via /janitor-memory-write / /janitor-memory-update (clean-the-fact-in-place + demote-the-error-to-a-[^N]-lesson). Unprompted.
  • MAINTAIN THE PROJECT WIKIMEM — proactively keep this project's PROJECT-scope pages (.claude/project/memory/) current so architecture facts and design lessons are git-tracked and shared with every dev, not stranded in one session.
  • SCOPE ROUTING — machine-private (local paths, usernames, hostnames, secrets) → LOCAL; project-shared with NO private data → PROJECT; cross-project → USER; UNSURE → LOCAL (the safe scope).
  • PROPAGATE — when you spawn a sub-agent, include this same recall/write directive in its prompt. Memory discipline is inherited, not assumed.

Read the full file on GitHub · 41 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. 8d ago First seen · 41 lines · 947 tokens per session scan A 3a895e8b471b

Subscribe to this mod's changes

ai-maestro-architect-agent CLAUDE.md is an instructions file published in the GitHub repository Emasoft/ai-maestro-architect-agent (2 stars, last pushed 10d ago), licensed MIT. It adds 947 tokens to every session, about $0.0047 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens