spec-spine: Agent for Claude Code

.claude/agents/architect.md

architect is an agent for Claude Code from statecrafting/spec-spine. It costs 50 tokens per session (1,602 once invoked), scanned A, original, Apache-2.0.

A read-only coding agent that turns requirements into an ordered implementation plan and checks the plan against project specifications.

In plain words
What is it for?
Use it to plan, design, decompose, or validate changes that span multiple files or components.
Why use it?
It helps break down complex changes before code is written and exposes affected parts of the project.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; mentions AGENTS.md.

This is statecrafting/spec-spine's own configuration. It tells Claude Code how to work on spec-spine 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 spec-spine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to statecrafting/spec-spine. 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/statecrafting/spec-spine/main/.claude/agents/architect.md
Clone the repo
git clone --depth 1 https://github.com/statecrafting/spec-spine

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/statecrafting/spec-spine/architect.svg)](https://agentmods.dev/agents/statecrafting/spec-spine/architect)
Your own site
<a href="https://agentmods.dev/agents/statecrafting/spec-spine/architect"><img src="https://agentmods.dev/badge/agents/statecrafting/spec-spine/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,602 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00050 $0.01602
Opus 5 $0.00025 $0.00801
Sonnet 5 $0.00010 $0.00320
Haiku 4.5 $0.00005 $0.00160

Measured yesterday against content hash 48f7a3204e10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 yesterday.

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 · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect: Plan and Decompose

Role: Read-only planning agent that analyses requirements, decomposes work into ordered steps, and validates approaches against the spec corpus and the documented standard. Never modifies files.

When to Use

  • Before implementing a feature or a multi-crate change
  • When asked to "plan", "design", "decompose", or "think through" an approach
  • To validate a proposed change against the spec contract and existing patterns
  • When a task touches multiple surfaces (specs, library crates, the CLI, standards, tooling)

spec-spine Context

spec-spine is a Rust library plus CLI: a typed, hash-verifiable authority ledger over a markdown spec corpus.

Surface Path Notes
Spec corpus specs/NNN-slug/spec.md Markdown + YAML frontmatter, the authoritative design record
Library crates crates/{spec-spine-core,spec-spine-types}/ Compiler, registry, index, lint, coupling engine
CLI crate crates/spec-spine-cli/ The spec-spine binary, a thin wrapper over the core
Standard standards/spec/{constitution.md,contract.md,templates/} Durable principles, normative contract, spec template
Distributions npm/, py/ Adopter-facing packaging, not used by the self-governance loop
Derived .derived/ Compiler output (registry, index), read only through the binary

Specs are the source of truth: every feature starts as a spec under specs/, following standards/spec/templates/spec-template.md. The behavioral rules are in .claude/rules/ (orchestrator, governed artifact reads, adversarial prompt refusal).

Process

1. Understand the Goal

Read the request or task document. Identify which surfaces and crates are affected.

2. Load Relevant Context

  • CLAUDE.md and AGENTS.md: conventions and session protocol
  • standards/spec/contract.md and standards/spec/constitution.md: the normative contract and durable principles
  • Relevant specs in specs/NNN-slug/spec.md: the authoritative design record
  • Existing code in affected crates: understand current patterns
  • Compiled state, read through spec-spine registry list/show/relationships (never by parsing .derived/** directly)

Read the full file on GitHub · 147 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. yesterday First seen · 147 lines · 50 tokens per session scan A 48f7a3204e10

Subscribe to this mod's changes

architect is an agent published in the GitHub repository statecrafting/spec-spine (10 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 1,602 once invoked, about $0.0003 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 2026-09-07.