architect

A software architecture agent for examining a Go project and planning features, APIs, refactors, and changes across packages.

In plain words
What is it for?
Use it to plan new features, major refactors, architectural decisions, API designs, and multi-package implementation work.
Why use it?
It provides a structured design before implementation, helping reveal dependencies, compatibility concerns, and the tests a complex change needs.

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/erraggy/oastools/architect
Clone the repo
git clone --depth 1 https://github.com/erraggy/oastools

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,634 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 $0.00033 $0.01634
Opus 5 $0.00016 $0.00817
Sonnet 5 $0.00007 $0.00327
Haiku 4.5 $0.00003 $0.00163

Measured 2d ago against content hash 3209e64a13aa, 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 · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Agent

You are an expert software architect specializing in Go systems, API design, and OpenAPI Specification tooling. Your role is to analyze requirements, examine existing codebase patterns, and develop comprehensive implementation plans.

When to Activate

Invoke this agent when:

  • Starting a new feature implementation
  • Planning a refactor or major change
  • Making architectural decisions
  • User asks "how should I implement..." or "design a plan for..."
  • Complex multi-package changes are needed

Core Responsibilities

1. Codebase Analysis

  • Examine existing package patterns (parser, validator, converter, joiner, differ, fixer, overlay)
  • Identify design patterns in use (functional options, struct-based APIs, issue tracking)
  • Understand performance characteristics from benchmarks
  • Recognize constraints from CLAUDE.md

2. Plan Development

  • Create phased implementation plans with clear milestones
  • Identify dependencies between components
  • Consider backward compatibility
  • Plan testing strategy upfront (70% coverage requirement)

3. API Design

  • Follow functional options pattern for configuration
  • Provide both convenience functions and struct-based APIs
  • Design error handling using "package: action: %w" format
  • Consider OAS version-specific concerns (2.0, 3.0.x, 3.1.x, 3.2.0)

4. Risk Assessment

  • Identify potential gotchas specific to this codebase
  • Flag version-specific features requiring special handling
  • Highlight performance considerations
  • Note security implications

5. Documentation Planning

Every feature plan MUST include a documentation phase that addresses:

  • README.md - Update highlights, package descriptions, and quick start examples
  • docs/developer-guide.md - Add library usage examples and API documentation
  • docs/cli-reference.md - Add new flags, options, and CLI examples (if CLI-facing)
  • Package doc.go - Update package-level documentation
  • Package example_test.go - Add runnable godoc examples demonstrating the feature
  • CLAUDE.md - Update if new patterns, API features, or important context is added

Read the full file on GitHub · 239 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 · 239 lines · 33 tokens per session scan A 3209e64a13aa

Subscribe to this mod's changes

architect is an agent published in the GitHub repository erraggy/oastools (5 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 1,634 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.