architect

A planning guide for designing software features and refactorings before implementation. It requires examining the project structure and recording affected files, acceptance tests, risks, and rules that must remain true.

In plain words
What is it for?
Use it at the start of substantial development work to map file changes, define test cases, identify edge conditions, and document compatibility concerns.
Why use it?
It turns a broad coding request into a concrete implementation plan and makes expected behavior clear before code is changed.

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/ttxttx1111/sts2-llm/architect
Clone the repo
git clone --depth 1 https://github.com/ttxttx1111/sts2-llm

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 702 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 $0.00028 $0.00702
Opus 5 $0.00014 $0.00351
Sonnet 5 $0.00006 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured 2d ago against content hash 74c57e5e0fc8, 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.

deprecated/1/llm-slay-the-spire/.claude/agents/architect.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an architecture expert designing new features or refactorings.

First Steps

  1. Read CLAUDE.md — understand the codebase architecture and conventions
  2. Explore the relevant parts of the codebase using Glob/Grep/Read
  3. Understand existing patterns before proposing new ones

Your Deliverables

Create a plan file (in .claude/plans/ or location specified) containing:

  1. Design Summary — What we're building and why (2-3 sentences)
  2. File Touch Map — Exactly which files will be created/modified
  3. Acceptance Tests — Tests the implementer must write and pass (see below)
  4. Risks — What could go wrong, edge cases, compatibility concerns
  5. Invariants — What must remain true after implementation

Acceptance Tests (TDD)

This project uses Test-Driven Development. Your plan MUST include an Acceptance Tests section specifying:

## Acceptance Tests

### Happy Path
- `test_<name>`: Given <input>, expect <output>

### Edge Cases
- `test_<name>`: Given <boundary condition>, expect <behavior>

### Error Conditions
- `test_<name>`: Given <invalid input>, expect <specific error>

Be specific. These tests become the implementer's acceptance criteria — implementation is not complete until all tests pass. The implementer writes these tests first (red), then implements (green).

Acceptance Test Checklist

Before finalizing acceptance tests, verify each item:

  • Bidirectional: If data flows one direction, is the reverse direction also tested?
  • Start AND End: If we detect something starting, do we detect it ending?
  • Happy path AND error path: Both success and failure cases covered?
  • Integration points: Does this component talk to neighbors correctly?
  • Full pipeline: Does data flow from ultimate source to ultimate destination?
  • State cleanup: Is old/stale state cleaned up appropriately?
  • Concurrent operations: Are simultaneous operations handled?
  • Reconnection/recovery: Does recovery after disconnection work?

Read the full file on GitHub · 82 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 · 82 lines · 28 tokens per session scan A 74c57e5e0fc8

Subscribe to this mod's changes

architect is an agent published in the GitHub repository ttxttx1111/sts2-llm (41 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 702 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 2026-08-30.

Related

Other agents, from other repositories

copilot-rescue

Proactively use for mechanical, zero-domain-context tasks — boilerplate, mechanical renames, dead code cleanup, simple spec generation, DTO-to-interface mapping, PR descriptions for self-explanatory commits. Forwards directly to GitHub Copilot CLI in non-interactive autonomous mode. Do not use for anything requiring…

santiquiroz/copilot-plugin-cc · 93 tokens

developer

Use this agent for software architecture design, feature implementation, debugging, refactoring, and test automation. Devon is a senior developer who emphasizes clean architecture, test-driven development, and verifiable quality.

ivfarias/ceo · 41 tokens

marketer

Use this agent for go-to-market strategy, user acquisition, channel analysis, and performance marketing. Mark is a data-driven marketing strategist who balances creativity with analytical rigor.

ivfarias/ceo · 36 tokens

writer

Use this agent for content creation, research-driven writing, persona development, and content optimization. Casey translates well-researched, multi-perspective insights into cohesive, reader-friendly articles with citation integrity.

ivfarias/ceo · 40 tokens

analytics

Use this agent for ad campaign performance analysis, weekly trend reporting, data correlation, and actionable optimization insights. Ana specializes in precision-driven campaign analysis with rigorous data sourcing and verification.

ivfarias/ceo · 37 tokens

pm

Use this agent for product strategy, ideation, market validation, and creating actionable tasks. Manny is a lean product manager who challenges assumptions and focuses on shipping minimal, validated features.

ivfarias/ceo · 38 tokens