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 ashtonian/llm-init --skill decomposegit clone --depth 1 https://github.com/ashtonian/llm-initWrote 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/ashtonian/llm-init/decompose)<a href="https://agentmods.dev/skills/ashtonian/llm-init/decompose"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/decompose/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/ashtonian/llm-init/decompose"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/decompose.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 | $0.00392 |
| Opus 5.5 | $0.00004 | $0.00157 |
| Sonnet 5.5 | $0.00002 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
decompose 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.
What it actually says
Break the following request into parallel tasks for agent team execution.
Instructions
- Read
docs/spec/.llm/PROGRESS.mdfor codebase patterns and prior context. - Read
docs/spec/.llm/STRATEGY.mdfor the current project decomposition. - Read
.claude/rules/agent-guide.mdfor tech stack and quality gates. - Verify a technical spec exists for this work. If no spec exists, the first task must be "Create technical specification" using
codegen.plan.llmas a reference for spec contents. - Decompose the request into 2-8 independent subtasks following these rules:
- Each task should take 75-150 Claude turns
- Size test: If you can't describe a task in 2-3 sentences, split it further
- Each task must be completable in one fresh context window
- Prefer wide not deep -- maximize independent tasks, minimize dependency chains
- Use
## Dependencies: Tasks NN, NNformat for ordering - Each task must have its own
## Verificationcommands - Each task must be self-contained (an agent with no prior context can execute it)
- For each task, create a file in
docs/spec/.llm/tasks/backlog/using the template:docs/spec/.llm/templates/task.template.md - Also create native tasks using TaskCreate for each task with appropriate blockedBy/blocks relationships.
- Update
docs/spec/.llm/STRATEGY.mdwith the decomposition. - Present the task list with dependencies to the user for approval.
Request
$ARGUMENTS
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 · 32 lines · 11 tokens per session scan A 73b7e12ab23e
decompose is a skill published in the GitHub repository ashtonian/llm-init (2 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 392 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 2026-08-31.
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…