A task-decomposition command that expands a project specification into small implementation steps with exact files and code locations. Its output is guidance for an implementer, not the task list the execution engine runs.

Use it when a specification needs detailed steps for an agent or human to follow.

It makes complex work easier to execute while keeping the official task boundaries in the machine-readable task list.

How bredmond1019/claude-sdk-rs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. 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/bredmond1019/claude-sdk-rs/main/.claude/commands/breakdown.md

Clone the repo

git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/breakdown/github.svg)](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/breakdown)

Your own site

<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/breakdown"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/breakdown/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/breakdown"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/breakdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,327 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.03327
Opus 5.5	$0.00000	$0.01331
Sonnet 5.5	$0.00000	$0.00665
Haiku 4.5	$0.00000	$0.00333

Measured 11d ago against content hash d26fc0ee89ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

breakdown 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 11d 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.

.claude/commands/breakdown.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Breakdown — Decompose a task spec into agent-executable sub-steps.

Takes a spec from planning/ and produces a granular breakdown where every sub-step names exact file paths, class/function names, and what to write or change — precise enough for an agent (or a human) to execute without interpretation.

What consumes this. breakdown.md is a reading aid for the implementing context, not an executable artifact. Every SDLC engine executes planning/<spec-slug>/tasks.json and nothing else — no engine parses breakdown.md. So a breakdown changes what an implementer knows, never what the engine runs.

That has one consequence worth stating plainly: if the decomposition should change what gets executed — different task boundaries, a task split in two, a new dependency edge — it must be written back into tasks.json, not left in prose here (step 7a). A breakdown that quietly disagrees with tasks.json is worse than no breakdown, because the engine follows the JSON and the reviewer follows the prose.

Variables

$ARGUMENTS — the block ID to break down (e.g. BT.ticket.some-slug), or a path to a legacy tasks.md spec for a block with no record. If omitted, default to the current block identified via planning/status.md. If no spec exists for the current block, say so and suggest running /next to find the current block, then /generate-tasks <BlockID> to write its spec.

Instructions

Resolve the target spec (D65 stage 2 — the block record is the preferred source; tasks.md is a fallback for a block that predates the migration):
- Derive blockId from $ARGUMENTS (if it looks like a block ID) or from planning/status.md if $ARGUMENTS was omitted.
- Check planning/blocks/<blockId>.json (the block record, per block.schema.json): ls planning/blocks/<blockId>.json 2>/dev/null && echo RECORD_EXISTS || echo RECORD_MISSING.
- Check planning/<blockId>/tasks.json (the task list the engines execute — always read this regardless of which spec source is used): ls planning/<blockId>/tasks.json.
- If RECORD_EXISTS: the spec source is the block record + tasks.json. Read both.
- If RECORD_MISSING: fall back to legacy planning/<blockId>/tasks.md (or the path given directly in $ARGUMENTS) as the spec source, alongside tasks.json.
- If neither a block record nor a legacy tasks.md exists, stop and explain clearly.

Read the full file on GitHub · 263 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.

11d ago First seen · 263 lines · 0 tokens per session scan A d26fc0ee89ee

Subscribe to this mod's changes

breakdown is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,327 tokens. 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 2026-10-26.

Planning

breakdown next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
breakdownbredmond1019/claude-sdk-rs	Command	23	1mo ago	Apache-2.0	A	0	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

claude-sdk-rs: Command for Claude Code