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 megamen32/LastHumanCommit --skill task-decompositiongit clone --depth 1 https://github.com/megamen32/LastHumanCommitWrote 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/megamen32/lasthumancommit/task-decomposition)<a href="https://agentmods.dev/skills/megamen32/lasthumancommit/task-decomposition"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/task-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/megamen32/lasthumancommit/task-decomposition"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/task-decomposition.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 | $0.00043 | $0.01190 |
| Opus 5.5 | $0.00017 | $0.00476 |
| Sonnet 5.5 | $0.00009 | $0.00238 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
task-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 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Decomposition
Decompose for faster business proof, not for more process artifacts.
Procedure
- Write one accepted business outcome and one shortest real canary.
- Draw only hard dependencies on the actual consumer path.
- Cut at independent ownership, artifact, decision, or acceptance boundaries.
- Give each leaf one owner, one output or business proof, one primary check, allowed paths, excluded scope, and a minimum/maximum active-time estimate.
- Estimate each coherent leaf from the work and its proof: minimum, maximum, basis in known steps or comparable evidence, and the specific uncertainty that separates the bounds. Aim for subtasks estimated at about 30 minutes, including verification; this is planning granularity, not a runtime cutoff. Smaller natural results need no padding. Split larger work at meaningful proof boundaries before execution. Twenty minutes is a reporting checkpoint, not a planning quantum or duration target.
- Parallelize leaves only when they do not require the same unresolved decision or conflicting writes. Put the critical canary path first.
- Remove coordination-only leaves whose output cannot change implementation, unblock another leaf, or prove the accepted result.
Derive the total before quoting it
Show the dependency graph and available execution slots, including any Lead work that occupies a slot. Identify which ready leaves actually run concurrently. For every serialized pair, name its dependency, shared mutable resource or capacity limit. Dispatch ready independent work when capacity exists; a diagram of parallel lanes followed by sequential execution is not parallel delivery.
Separate three quantities:
- Work effort: sum of the leaf estimates, including each leaf's verification.
- Delivery duration: the planned capacity-respecting critical path or execution waves; parallel work contributes the longest lane, not the sum of all lanes.
- External waits: queue, approval, build service or unavailable environment, listed separately with their evidence or marked unknown.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +15 lines · -8 tokens per session 41eae16dae9b
- 1mo ago Changed · +43 lines fd5510f4ecca
- 1mo ago First seen · 54 lines · 51 tokens per session scan A a87e3646da8c
task-decomposition is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,190 once invoked, about $0.0002 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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…