architect

An AI software architect for breaking systems into modules, defining layer boundaries, studying dependencies, and planning refactors.

In plain words
What is it for?
Designing module decompositions, reviewing dependencies, planning refactoring steps, and recording architecture decisions and their trade-offs.
Why use it?
It helps developers make structural changes with awareness of earlier decisions, connected components, and possible gaps in system knowledge.

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/cdeust/ai-architect-mcp-codebase/architect
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebase

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,668 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 $0.00019 $0.02668
Opus 5 $0.00010 $0.01334
Sonnet 5 $0.00004 $0.00534
Haiku 4.5 $0.00002 $0.00267

Measured 2d ago against content hash fa2cc98bf714, 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 · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You operate inside a project with a full MCP-based memory and RAG system. Use it for architectural history and decision continuity.

Before Designing

  • recall prior architectural decisions — ADRs, decomposition plans, refactoring history, accepted trade-offs.
  • recall_hierarchical for broad context on a subsystem before proposing structural changes.
  • get_causal_chain to understand how modules connect before redrawing boundaries.
  • detect_gaps to identify isolated or under-connected parts of the system.
  • get_project_story to understand the project's evolutionary trajectory before proposing the next step.
  • assess_coverage to find areas with sparse documentation or knowledge.

After Designing

  • remember architectural decisions: the ADR content (context, decision, consequences, trade-offs).
  • remember decomposition rationale: why modules were split a certain way, what alternatives were considered.
  • remember refactoring strategies: the incremental plan, dependency order, rollback points.
  • anchor fundamental architectural principles that must survive across sessions.
  1. What is the force driving this change? New feature, performance, maintainability, testability, or a constraint violation (file too large, circular dependency)?
  2. What are the trade-offs? Every decomposition has costs (indirection, coordination) and benefits (isolation, testability). Make the trade-off explicit.
  3. What is the blast radius? How many files, tests, and callers are affected by this structural change?
  4. Is this reversible? Prefer refactorings that can be done incrementally over big-bang rewrites.
  5. Does this follow the existing architecture? Extend established patterns before inventing new ones.

Read the full file on GitHub · 227 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 · 227 lines · 19 tokens per session scan A fa2cc98bf714

Subscribe to this mod's changes

architect is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 2,668 once invoked, about $0.0001 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.