code-decompose

code-decompose is a skill for Claude Code, Codex from roarista/awesome-harness. It costs 114 tokens per session (1,175 once invoked), scanned A, original, MIT.

A planning workflow that breaks a substantial code change into small units that can each be built and checked independently.

In plain words
What is it for?
Planning features, bug fixes, refactors, and new modules, then assigning each unit to a builder and reviewing it against the same specification.
Why use it?
It makes the intended change explicit before coding and limits the risk of large, difficult-to-review edits.

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/roarista/awesome-harness/code-decompose
Any agent
npx skills add roarista/awesome-harness --skill code-decompose
Clone the repo
git clone --depth 1 https://github.com/roarista/awesome-harness

Made for: Claude Code, Codex.

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 code-decompose

README.md
[![agentmods](https://agentmods.dev/badge/skills/roarista/awesome-harness/code-decompose.svg)](https://agentmods.dev/skills/roarista/awesome-harness/code-decompose)
Your own site
<a href="https://agentmods.dev/skills/roarista/awesome-harness/code-decompose"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/code-decompose.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,175 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 $0.00114 $0.01175
Opus 5 $0.00057 $0.00588
Sonnet 5 $0.00023 $0.00235
Haiku 4.5 $0.00011 $0.00118

Measured 3d ago against content hash e59d6a9957d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-decompose 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 3d 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.

codex/skills/code-decompose/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

code-decompose (Codex edition)

Steps 4-6 of THE PROCEDURE (~/.codex/AGENTS.md). Entry condition: codebase-first already returned a BUILD gate plus the residual gap. If it hasn't run, run it first — do not re-discover here.

The point: the change must be fully understood before any code is written — the code that exists and the code you intend to write — and that understanding must be written down precisely enough that it could be executed without further judgment. Decomposition is the expensive thinking step; execution is the cheap step done at volume.

Use one bounded Codex builder per unit and a distinct auditor against the same spec when native subagents are available. Never run sibling builders concurrently in a dirty checkout. If subagents are unavailable, preserve the separation in time: finish specing, build, then re-read the diff against the spec with independent-auditor eyes.

Phase 1 — Decompose (write the specs first, no code)

Start from the codebase-first discovery artifact (.scratch/discovery/<slug>.md if present) and carry its REUSE/ADAPT/REJECT verdicts and gate forward verbatim. Then produce:

  1. Understanding (3-6 lines): what exists now with file:line anchors, what we want, and the gap. Include the REUSE/ADAPT/REJECT decisions and the STOP/PLAN/BUILD gate. If the gate is STOP or PLAN, output that with its reasoning instead of Units and hand back to Ro.
  2. Units — the gap split into the smallest independently-verifiable pieces. Keep splitting until each is mechanical. Each unit is self-contained:
UNIT <n>: <one-line title>
  CONTEXT  — what exists, with file:line. Exactly the code/state you will touch.
  REUSE    — the exact REUSE/ADAPT decisions + source anchors; no invented APIs;
             CHANGE covers only the residual gap.
  CHANGE   — exactly what to write/modify. One correct interpretation only.
  GOAL     — the outcome this unit produces and why.
  VERIFY   — the concrete check that proves this unit is done: the command, the test,
             the expected output, or the file state. Defined BEFORE execution.
  DEPENDS  — which units must land first (this is your execution order).

Read the full file on GitHub · 70 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. 3d ago First seen · 70 lines · 114 tokens per session scan A e59d6a9957d7

Subscribe to this mod's changes

code-decompose is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 8d ago), licensed MIT. It adds 114 tokens to every session and 1,175 once invoked, about $0.0006 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.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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