Borrowing it
Nothing to install: this file belongs to squirrelsoft-dev/dev. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/squirrelsoft-dev/dev/main/.claude/commands/breakdown.mdgit clone --depth 1 https://github.com/squirrelsoft-dev/devWrote 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.
[](https://agentmods.dev/commands/squirrelsoft-dev/dev/breakdown)<a href="https://agentmods.dev/commands/squirrelsoft-dev/dev/breakdown"><img src="https://agentmods.dev/badge/commands/squirrelsoft-dev/dev/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.
<a href="https://agentmods.dev/commands/squirrelsoft-dev/dev/breakdown"><img src="https://agentmods.dev/badge/commands/squirrelsoft-dev/dev/breakdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00011 | $0.00658 |
| Opus 5.5 | $0.00004 | $0.00263 |
| Sonnet 5.5 | $0.00002 | $0.00132 |
| Haiku 4.5 | $0.00001 | $0.00066 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Breakdown
Use the Task tool to spawn a Plan agent in plan mode to break down the following task: $ARGUMENTS
Important - This agent does not produce code or create any output other than generating the complete tasks file.
The agent should:
- Understand — Restate the task. Ask clarifying questions if the scope is ambiguous.
- Research — Read relevant files to understand the codebase, architecture, and existing patterns.
- Find relevant skills — Search for community skills that may help with the task or its subtasks. Run
npx skills find <topic>for key technologies or patterns involved. If a relevant skill is found, runnpx skills add <owner/repo@skill>to install it. Installed skills will be available to all agents during implementation. - Decompose — Break the task into the smallest meaningful units of work.
- Identify dependencies — For each task, determine if it is:
- Non-blocking — independent, can be done anytime
- Blocked by — cannot start until specific other tasks complete (list them)
- Blocking — other tasks cannot start until this one completes (list them)
- Group for parallelism — Organize tasks into groups that can be worked on simultaneously. Tasks in the same group have no dependencies on each other. Later groups depend on earlier groups.
- Save — Create the
.claude/tasks/directory if needed, then write the breakdown to.claude/tasks/$ARGUMENTS.md(kebab-case the filename).
Output Format
# Task Breakdown: <feature name>
> <one-sentence summary>
## Group 1 — <label>
_Tasks in this group can be done in parallel._
- [ ] **Task title** `[S/M/L]`
<what to do and why>
Files: `path/to/file`
Blocking: <task titles this enables, or "None">
- [ ] **Task title** `[S/M/L]`
<what to do and why>
Files: `path/to/file`
Non-blocking
## Group 2 — <label>
_Depends on: Group 1_
- [ ] **Task title** `[S/M/L]`
<what to do and why>
Files: `path/to/file`
Blocked by: <task titles from earlier groups>
Blocking: <task titles in later groups, or "None">
## Group N — <label>
_Depends on: Group N-1_
- [ ] **Task title** `[S/M/L]`
<what to do and why>
Files: `path/to/file`
Blocked by: <task titles from earlier groups>
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.
- 1mo ago First seen · 67 lines · 11 tokens per session scan A ef8974705a9e
breakdown is a command published in the GitHub repository squirrelsoft-dev/dev (17 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 658 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-01.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
sync-linear
Sync current work with Linear ticket status.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.