split-architecture

A specification-organizing tool that converts one large architecture document into a directory of smaller files. An architecture document explains how a software system is structured and why key technical choices were made.

In plain words
What is it for?
Use it when an architecture document has grown beyond the stated size or decision-record thresholds, or when you want to split it manually.
Why use it?
Smaller files make large architecture documentation easier to maintain and let an agent load only the relevant decisions.

Skill for Claude CodeCodex

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 skills/etr/groundwork/split-architecture
Any agent
npx skills add etr/groundwork --skill split-architecture
Clone the repo
git clone --depth 1 https://github.com/etr/groundwork

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,854 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 $0.00027 $0.01854
Opus 5 $0.00014 $0.00927
Sonnet 5 $0.00005 $0.00371
Haiku 4.5 $0.00003 $0.00185

Measured 2d ago against content hash 9cb34fbb9b96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

split-architecture 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.

skills/split-architecture/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Split Architecture Skill

Converts a single-file architecture document ({{specs_dir}}/architecture.md) into a directory-based format ({{specs_dir}}/architecture/) for better organization and targeted context loading.

When to Use

  • Automatically by design-architecture and source-architecture-from-code when the single-file architecture doc crosses 500 lines or 10 decision records (sections matching ### DR-\d+)
  • Manually when the user invokes /split-architecture

Step 0: Resolve Project Context

  1. Monorepo check: Does .groundwork.yml exist at the repo root?
    • If yes → Is {{project_name}} non-empty?
      • If empty → Invoke Skill(skill="groundwork:select-project") to select a project, then restart this skill.
      • If set → Project is {{project_name}}, specs at {{specs_dir}}/.
    • If no → Continue (single-project repo).
  2. Proceed with the resolved project context.

Step 1: Validate Preconditions

  1. Check single file exists: {{specs_dir}}/architecture.md must exist
    • If missing → output "No single-file architecture doc found at {{specs_dir}}/architecture.md. Nothing to split." and stop.
  2. Check directory does NOT exist: {{specs_dir}}/architecture/ must not already exist
    • If it exists → output "Architecture doc is already in directory format at {{specs_dir}}/architecture/. Nothing to do." and stop.
  3. Read the file and count lines and decision records (sections matching ^### DR-\d+).

Step 2: Split the File

Parse the single-file architecture doc into sections and write each to its own file under {{specs_dir}}/architecture/.

Directory Structure

{{specs_dir}}/architecture/
├── _index.md                 # Header, metadata
├── 01-executive-summary.md   # Section 1: Executive Summary
├── 02-architectural-drivers.md # Section 2: Architectural Drivers
├── 03-system-overview.md     # Section 3: System Overview
├── 04-components/            # Section 4: One file per component
│   ├── _index.md             # Section 4 header ("## 4) Component Details")
│   └── <component-slug>.md   # e.g., cli.md, query-router.md
├── 05-data.md                # Section 5: Data Architecture
├── 06-integration.md         # Section 6: Integration Architecture
├── 07-security.md            # Section 7: Security Architecture
├── 08-infrastructure.md      # Section 8: Infrastructure & Deployment
├── 09-observability.md       # Section 9: Observability
├── 10-cost-model.md          # Section 10: Cost Model
├── 11-decisions/             # Section 11: One file per DR
│   ├── _index.md             # Section 11 header ("## 11) Decision Records")
│   └── DR-NNN.md             # e.g., DR-001.md, DR-015.md
├── 12-open-questions.md      # Section 12: Open Questions & Risks
└── 13-appendices.md          # Section 13: Appendices

Read the full file on GitHub · 146 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 · 146 lines · 27 tokens per session scan A 9cb34fbb9b96

Subscribe to this mod's changes

split-architecture is a skill published in the GitHub repository etr/groundwork (42 stars, last pushed 20d ago), licensed MIT. It adds 27 tokens to every session and 1,854 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens