work-unit-decomposition

work-unit-decomposition is a skill for Claude Code from a5c-ai/babysitter. It costs 32 tokens per session (352 once invoked), scanned A, original, MIT.

A planning method that breaks a large implementation into separate work units with completion checklists, file limits, dependencies, and approval points.

In plain words
What is it for?
Use it to define what each unit must finish, which files it may change, what it depends on, and whether it can run in parallel.
Why use it?
It makes complex work easier to schedule, review, and execute without hidden dependencies or uncontrolled edits.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Good fit Use it to define what each unit must finish, which files it may change, what it depends on, and whether it can run in parallel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a5c-ai/babysitter/work-unit-decomposition
About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,778 stars · on GitHub · a5c.ai

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.

Any agent
npx skills add a5c-ai/babysitter --skill work-unit-decomposition
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

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 work-unit-decomposition

README.md
[![agentmods](https://agentmods.dev/badge/skills/a5c-ai/babysitter/work-unit-decomposition.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/work-unit-decomposition)
Your own site
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/work-unit-decomposition"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/work-unit-decomposition.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 352 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00032 $0.00352
Opus 5 $0.00016 $0.00176
Sonnet 5 $0.00006 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 5d ago against content hash cb86766ca10c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

work-unit-decomposition 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 5d 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.

library/methodologies/metaswarm/skills/work-unit-decomposition/SKILL.md · 44 lines

What it actually says

  • When decomposing a large feature into implementable chunks
  • When preparing for orchestrated execution

Work Unit Structure

Each work unit specifies:

  • ID - Unique identifier
  • Title - Human-readable description
  • Definition of Done - Enumerated checklist items
  • File Scope - Which files the unit may modify
  • Dependencies - Other work units this depends on
  • Human Checkpoint - Whether human approval is needed before execution
  • Parallel Safe - Whether it can execute alongside other units

Human Checkpoint Triggers

Mark human checkpoints for:

  • Schema or database changes
  • Security-sensitive code paths
  • New architectural patterns not seen in codebase
  • External API integrations
  • Breaking changes to public interfaces

Agents Used

  • agents/architect/ - Creates the decomposition
  • agents/cto/ - Validates TDD readiness per unit

Tool Use

Invoke as part of: methodologies/metaswarm/metaswarm-orchestrator (Phase 4)

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 44 lines · 32 tokens per session scan A cb86766ca10c

Subscribe to this mod's changes

work-unit-decomposition is a skill published in the GitHub repository a5c-ai/babysitter (1,778 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 352 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 2026-09-03.