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.
npx agentmods add skills/ibrain-bvba/gutt-claude-code-plugin/sub-task-breakdownnpx skills add iBrain-BVBA/gutt-claude-code-plugin --skill sub-task-breakdowngit clone --depth 1 https://github.com/iBrain-BVBA/gutt-claude-code-pluginWrote 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/skills/ibrain-bvba/gutt-claude-code-plugin/sub-task-breakdown)<a href="https://agentmods.dev/skills/ibrain-bvba/gutt-claude-code-plugin/sub-task-breakdown"><img src="https://agentmods.dev/badge/skills/ibrain-bvba/gutt-claude-code-plugin/sub-task-breakdown.svg" alt="Measured on agentmods" 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 | $0.00133 | $0.02747 |
| Opus 5 | $0.00067 | $0.01373 |
| Sonnet 5 | $0.00027 | $0.00549 |
| Haiku 4.5 | $0.00013 | $0.00275 |
Grade A, and why
sub-task-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 4d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-task Breakdown
A story that is too big to start is usually not too big to describe — the pieces are known, they were just never written down, and so nobody can begin, estimate, or parallelize. This skill writes them down: a small set of sub-tasks, each with acceptance criteria a reviewer could actually check, an effort range grounded in comparable past work, and the dependencies that fix their order. The output is a proposal. Which slices are right, and whether they get filed at all, stays with the team.
Underneath, memory-search owns the search ladder and the relevance gate,
graph-traversal owns relationship walking when a summary names a thing
without stating it, and memory-capture owns any durable write; all three ship
with the gutt-pro plugin (this plugin depends on it) — without them, follow the
rules below and note the gap in one line. Jira access comes from whatever Atlassian tooling the session
surfaces; find it in your tool list — names and prefixes vary per install.
Hard rules (non-negotiable — read first)
- Jira is read-only by default; filing is a gated exception. Never touch the parent story — not its description, not its acceptance criteria, not its fields, not its status. Divergence from the parent goes in the proposal, and in a comment if the user approves one; the story's own text is the author's. Sub-tasks are created only when the user asks for them in this session and approves the exact set — titles, criteria, and links as they will be written. Creating issues is outward-facing and not undone by an apology: approval is the gate, and silence is not approval. The other permitted write is one comment, on the same exact-text terms.
- Jira's vocabulary only — no other tracker's mechanics in the output. A
dependency is a Jira issue link, named the way that project names it
(rule 8); a parent is the parent field of a sub-task issue type; acceptance
criteria are text in the sub-task's own description. No
#123references, noCloses #…trailers, no checklist-as-linking — whatever tracker the session exposes, this skill emits Jira. That includes foreign references quoted from the parent's own text, which is where they usually get in: translate each to the Jira key it means, or name it as untranslatable — "the parent cites#412, which does not resolve to a Jira issue; ask the author which ticket it means." Never pass one through unaccounted.
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.
- 4d ago First seen · 214 lines · 133 tokens per session scan A bce572e31a62
sub-task-breakdown is a skill published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (5 stars, last pushed 2d ago), licensed MIT. It adds 133 tokens to every session and 2,747 once invoked, about $0.0007 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…