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/kcdjmaxx/homaruscc/writenpx skills add kcdjmaxx/HomarUScc --skill writegit clone --depth 1 https://github.com/kcdjmaxx/HomarUSccWhat 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 | $0.00079 | $0.01996 |
| Opus 5 | $0.00039 | $0.00998 |
| Sonnet 5 | $0.00016 | $0.00399 |
| Haiku 4.5 | $0.00008 | $0.00200 |
Grade A, and why
write 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 2d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write
A structured writing pipeline that produces research-backed articles with intermediate artifacts at every stage.
Usage
When the user invokes /write, they provide a topic. Optionally:
--audience <who>— target reader (default: general/informed)--format <type>— blog, article, white-paper, linkedin, newsletter (default: article)--voice <whose>— max, caul, neutral (default: max)--length <words>— target word count (default: 1500)--no-review— skip the human review gate before delivery--background— run the entire pipeline as a background agent
If key parameters are missing (audience, format), ask once before starting. Don't over-interrogate — make reasonable defaults and move.
Output Directory
All artifacts go to ~/.homaruscc/writing/<slug>/ where <slug> is a URL-safe version of the topic.
~/.homaruscc/writing/<slug>/
research.md — raw research notes
outline.md — structured outline
draft-v1.md — first draft
critique.md — self-critique notes
draft-final.md — polished final
meta.json — parameters, timestamps, status
Pipeline
Step 1: Clarify (if needed)
If the user didn't specify audience, format, or voice, ask a single clarifying question with sensible defaults offered. If they said enough, skip this and use defaults.
Always ask: "Do you have any references to include? URLs, files, transcripts, or anything I should read before starting." If the user provides references (YouTube links, articles, documents), process them first — transcribe videos, fetch web content, read files — and include them in the research phase. If no references, move on.
Write meta.json with all parameters:
{
"topic": "...",
"audience": "...",
"format": "article",
"voice": "max",
"targetLength": 1500,
"references": [],
"status": "researching",
"created": "ISO timestamp",
"steps": {}
}
Step 2: Research
Three parallel research tracks:
- Web research — Use Perplexity-style deep search via
WebSearchtool. Run 3-5 queries from different angles on the topic. Capture key facts, statistics, expert quotes, and contrarian viewpoints.
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.
- 2d ago First seen · 212 lines · 79 tokens per session scan A e11d06169236
write is a skill published in the GitHub repository kcdjmaxx/HomarUScc (1 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 1,996 once invoked, about $0.0004 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…