A project-planning skill that breaks a project or development track into modules, maps their dependencies, and records the order they should be built. A monorepo or project can use these maps to keep architecture and implementation plans aligned.

Use it to create an architecture map for a project, or high-level and low-level design documents for a development track.

It makes large work easier to plan by showing which parts depend on others and which design documents are needed before implementation.

decompose — Skill by drafthq

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/drafthq/draft/decompose

Any agent

npx skills add drafthq/draft --skill decompose

Clone the repo

git clone --depth 1 https://github.com/drafthq/draft

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 9,023 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.

Model	Per session	Once invoked
Fable 5	$0.00071	$0.09023
Opus 5	$0.00036	$0.04512
Sonnet 5	$0.00014	$0.01805
Haiku 4.5	$0.00007	$0.00902

Measured 2d ago against content hash 953736b28bb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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/decompose/SKILL.md · 704 lines

How it starts

The opening of the file, as written. The whole thing — 704 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decompose

You are decomposing a project or track into modules with clear responsibilities, dependencies, and implementation order.

MANDATORY GRAPH LOOKUP (read before any analysis)

First resolve the bundled helpers:

# Locate Draft's bundled helpers (cwd is the user's project; ${CLAUDE_PLUGIN_ROOT}
# is not exported into skill Bash). See core/shared/tool-resolver.md.
DRAFT_TOOLS="${DRAFT_PLUGIN_ROOT:-$(cat ~/.cache/draft/plugin-root 2>/dev/null)}/scripts/tools"
[ -d "$DRAFT_TOOLS" ] || DRAFT_TOOLS="$(ls -d ~/.claude/plugins/cache/*/draft/*/scripts/tools 2>/dev/null | sort -V | tail -1)"
[ -d "$DRAFT_TOOLS" ] || DRAFT_TOOLS="$(ls -d ~/.claude/plugins/marketplaces/*draft*/scripts/tools 2>/dev/null | tail -1)"
[ -d "$DRAFT_TOOLS" ] || DRAFT_TOOLS="$PWD/scripts/tools"

When draft/graph/schema.yaml exists, this skill must follow the graph-first lookup contract in core/shared/graph-query.md §Mandatory Lookup Contract. Module identification (Step 3) and dependency mapping (Step 4) start from the graph:

Query "$DRAFT_TOOLS/graph-arch.sh" --repo . for the authoritative module list and fan-in/out.
Run "$DRAFT_TOOLS/hotspot-rank.sh" --repo . to identify candidate modules to split.
Use "$DRAFT_TOOLS/graph-callers.sh"/"$DRAFT_TOOLS/graph-impact.sh" on demand for symbols/callers inside a candidate module.
Run "$DRAFT_TOOLS/cycle-detect.sh" --repo . to enumerate existing cycles before proposing new boundaries.

Filesystem grep/find for module discovery is only permitted after a documented graph miss, using the fallback sentence Graph returned no match for <X>; falling back to grep. and recorded in the Graph Usage Report.

Red Flags - STOP if you're

See shared red flags — applies to all code-touching skills. In particular, the Ground-Truth Red Flags are load-bearing for decompose: HLD/LLD are design-mandated artifacts and TBD citations on Modified modules fail review.

Read the full file on GitHub · 704 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.

2d ago First seen · 704 lines · 71 tokens per session scan A 953736b28bb8

Subscribe to this mod's changes

decompose is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 13d ago), licensed MIT. It adds 71 tokens to every session and 9,023 once invoked, about $0.0004 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.

Code review DevOps and cloud Testing ai-code-review ai-coding claude-code copilot cursor

decompose

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Decompose

MANDATORY GRAPH LOOKUP (read before any analysis)

Red Flags - STOP if you're

What this file has done since we first saw it

Other skills, from other repositories

memorix-memory

memorix

memorix-mini-skills

memorix-orchestrate

memorix-reasoning

memorix-troubleshooting