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/compactnpx skills add kcdjmaxx/HomarUScc --skill compactgit 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 | $0.00071 | $0.01217 |
| Opus 5 | $0.00036 | $0.00609 |
| Sonnet 5 | $0.00014 | $0.00243 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
compact 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compact
Hard character limits on identity files with intelligent LLM-assisted consolidation. Prevents unbounded growth by rewriting at higher information density, not by deleting.
Usage
/compact -- check all files, compact any over limit
/compact preferences.md -- compact a specific file
/compact --dry-run -- show what would change without writing
/compact --status -- show current sizes vs limits
How It Works
Step 1: Load Limits
Read ~/.homaruscc/config.json field identityLimits. Default limits (chars):
| File | Limit |
|---|---|
| soul.md | 8,000 |
| preferences.md | 4,000 |
| user.md | 3,000 |
| state.md | 2,000 |
| MEMORY.md | 5,000 (+ 200 lines) |
| disagreements.md | 1,500 |
| bisociations.md | 3,000 |
Identity files live at ~/.homaruscc/identity/. MEMORY.md lives at the project root.
Step 2: Measure Files
Read each file. Count characters. For --status, display a table:
File Chars Limit Pct Status
soul.md 7,200 8,000 90% OK
preferences.md 4,800 4,000 120% OVER - needs compaction
user.md 4,500 3,000 150% OVER - flagged for human review
...
Mark 100-110% as WARNING, >110% as OVER. Stop here if --status.
Step 3: Identify Targets
- Files >110% of limit: add to compaction queue
- Files 100-110%: log warning, skip (buffer zone)
user.md: NEVER auto-compact. If over limit, say: "user.md is over limit ({pct}%). This file requires human review -- I won't compact it automatically."
Step 4: Compact Each File
For each file in the queue, read its content and build a consolidation prompt using the per-file rules below. The LLM output IS the compacted content.
If --dry-run: show the proposed compacted version and character savings. Do not write.
Otherwise: write the compacted content back to the file.
Step 5: Log
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 · 128 lines · 71 tokens per session scan A c7aafa16358c
compact is a skill published in the GitHub repository kcdjmaxx/HomarUScc (1 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 1,217 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…