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/auto-skillnpx skills add kcdjmaxx/HomarUScc --skill auto-skillgit clone --depth 1 https://github.com/kcdjmaxx/HomarUSccWrote 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/kcdjmaxx/homaruscc/auto-skill)<a href="https://agentmods.dev/skills/kcdjmaxx/homaruscc/auto-skill"><img src="https://agentmods.dev/badge/skills/kcdjmaxx/homaruscc/auto-skill.svg" alt="Measured on agentmods" 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 | $0.00118 | $0.02219 |
| Opus 5 | $0.00059 | $0.01110 |
| Sonnet 5 | $0.00024 | $0.00444 |
| Haiku 4.5 | $0.00012 | $0.00222 |
Grade A, and why
auto-skill 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 4d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Skill
Detect when a workflow you just completed is reusable enough to become a skill, then generate a SKILL.md for it. Works in two modes: automatic detection during reflection, or explicit creation when the user asks.
Usage
/auto-skill -- detect skill candidates from recent session
/auto-skill <name> -- create a skill from a specific recent procedure
"make this a skill" -- explicit trigger (H3), works even if autoSkill.enabled is false
How It Works
Mode A: Automatic Detection (During Reflection)
This runs during the homaruscc event loop reflection step 4, after a local/howto/* memory has been stored.
Step 1: Check Config
Read ~/.homaruscc/config.json. If autoSkill.enabled is not true, skip detection entirely. If the key is missing or false, stop here and continue the event loop normally.
Step 2: Run Detection Heuristics
Evaluate each heuristic independently. Any single match is sufficient to flag a candidate.
H1 -- Complexity Threshold (R500): Count the tool calls from the current workflow. If 5 or more tool calls were made toward a single goal, this is a candidate.
H2 -- Recurrence Signal (R501): Search memory for existing howtos with keywords from the new howto:
memory_search: query="<keywords from new howto>" filter="local/howto/*"
If 2 or more existing local/howto/* entries match, this is a candidate.
H4 -- Reflection Similarity (R503): Search memory using the full text of the new howto:
memory_search: query="<full howto text>"
If the top result has >0.7 similarity score AND is a different memory key, this is a candidate.
Note: H3 (explicit request) is handled by Mode B below, not here.
Step 3: Evaluate Results
If no heuristic matched, continue the event loop -- no candidate.
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.
- 4d ago First seen · 266 lines · 118 tokens per session scan A 805c6b035c6f
auto-skill is a skill published in the GitHub repository kcdjmaxx/HomarUScc (1 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 2,219 once invoked, about $0.0006 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…