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 skills add tomzx/agents --skill create-tasks-decompositiongit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/create-tasks-decomposition)<a href="https://agentmods.dev/skills/tomzx/agents/create-tasks-decomposition"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-tasks-decomposition/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/skills/tomzx/agents/create-tasks-decomposition"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-tasks-decomposition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.01993 |
| Opus 5.5 | $0.00009 | $0.00797 |
| Sonnet 5.5 | $0.00005 | $0.00399 |
| Haiku 4.5 | $0.00002 | $0.00199 |
Grade A, and why
create-tasks-decomposition scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Tasks Decomposition
Breaks down a feature, plan, or specification into discrete, actionable tasks.
Each task gets its own file under .sdlc/features/N-<slug>/tasks/ with a unique sequence number, frontmatter status, and explicit dependencies.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, locate the feature directory under
.sdlc/features/whose frontmatterissuefield references$ISSUE_NUMBER. .sdlc/features/N-<slug>/plan.md(unified) or.sdlc/features/N-<slug>/plan/index.mdplus itsplan/<concern>.mdfiles (split) (must have passed review with findings verdictapproved), or an implementation plan/specification provided in context or as a file path ($1)
Task Sizing Guidelines
| Size | Effort | Description |
|---|---|---|
| XS | < 2h | Configuration change, single-file edit |
| S | 0.5d | Small feature, single component |
| M | 1d | Moderate feature, 2–5 files |
| L | 2d | Complex feature, multiple components |
| XL | > 2d | Must be broken down further |
Tasks estimated XL must be decomposed into smaller tasks before being considered actionable.
Steps
- Resolve and read the plan:
.sdlc/features/N-<slug>/plan.md(unified), otherwise.sdlc/features/N-<slug>/plan/index.mdtogether with everyplan/<concern>.mdit lists (split), otherwise the specification or a file path ($1). For a split plan, decompose tasks across all concern files as one combined backlog (thetasks/directory stays flat per feature, not per concern). - Identify all units of work, targeting tasks completable in 0.5–2 days each.
- For each task, define: description, acceptance criteria, effort size, and dependencies on other tasks.
- Order tasks and assign sequence numbers starting at
1within this feature. - Identify the critical path through the dependency graph (the chain with the greatest total effort).
- Write one file per task to
.sdlc/features/N-<slug>/tasks/N-<slug>.md, whereNrestarts at1for each feature. - Output the summary: task table followed by a Mermaid dependency graph with the critical path highlighted (see Output Format below).
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.
- 22d ago Changed · +3 lines d4593afed10a
- 23d ago Changed · -4 lines 7e5526759063
- 2mo ago First seen · 162 lines · 23 tokens per session scan A ec5c6196d066
create-tasks-decomposition is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 1,993 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…