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 decompose-and-dispatchgit 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/decompose-and-dispatch)<a href="https://agentmods.dev/skills/megamen32/lasthumancommit/decompose-and-dispatch"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/decompose-and-dispatch/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/decompose-and-dispatch"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/decompose-and-dispatch.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 | $0.00030 | $0.01132 |
| Opus 5.5 | $0.00012 | $0.00453 |
| Sonnet 5.5 | $0.00006 | $0.00226 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
decompose-and-dispatch 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decompose, allocate, execute, learn
Use before substantial dispatch and whenever execution reveals a bad boundary. For a trivial task, keep the graph implicit and compact; do not manufacture jobs.
Resolve uncertainty before distributing it
Specify the complete user outcome and its observable acceptance. Identify facts, unknowns, shared contracts and existing work. Lead/Adviser decides difficult architecture; use council where independent strong-model reasoning is valuable. Research can itself be parallelized when its questions are independent.
Create coherent nodes, not line-count or token-sized fragments. Each node has a
clear goal, known inputs, dependencies, owned mutable paths/resources, acceptance
check and next checkpoint. A cheap executor should not have to reconstruct the
whole architecture or choose an unmade product decision. Use
../model-routing/SKILL.md for each meaningful allocation.
Estimate each node from its actual work and verification: minimum/maximum minutes, known steps or comparable evidence, and the specific uncertainty widening the range. Decompose into subtasks estimated at about 30 minutes, including verification; this is planning granularity, never an actual execution cutoff or rejection rule. Split larger work at meaningful proof boundaries before dispatch, including direct Lead, review and testing work. Twenty minutes remains a checkpoint, not a duration target. Do not manufacture arbitrary time boxes or an overall range.
Parallelism with joins
A lane is ready only when its required input contracts/results exist. Independent work can run concurrently. Shared writes, a mutable input produced by another lane, shared test-account state and resource limits can make otherwise separate files dependent. Freeze interfaces, isolate mutable fixtures, designate one owner, or sequence the conflicting work. Do not parallelize dependent steps for appearance.
When a graph is useful, run the optional offline checker from the LastHumanCommit
repository: python3 scripts/lhc_validate_graph.py <graph.json>. See
references/execution-graph.json. The checker is repository tooling; installed
skills do not assume that a source checkout exists beside the common bundle.
It checks only declared path/dependency conflicts, not runtime semantics, resource
locks, real model capability or whether tasks are conceptually independent.
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 · +20 lines 1770e2e3e5c8
- 1mo ago First seen · 78 lines · 30 tokens per session scan A 24903eff89a7
decompose-and-dispatch is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 1,132 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 2026-09-05.
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…