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 SethGammon/Citadel --skill housecleangit clone --depth 1 https://github.com/SethGammon/CitadelWrote 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/sethgammon/citadel/houseclean)<a href="https://agentmods.dev/skills/sethgammon/citadel/houseclean"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/houseclean/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/sethgammon/citadel/houseclean"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/houseclean.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00089 | $0.02402 |
| Opus 5.5 | $0.00036 | $0.00961 |
| Sonnet 5.5 | $0.00018 | $0.00480 |
| Haiku 4.5 | $0.00009 | $0.00240 |
Grade A, and why
houseclean 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/houseclean — Storage Audit and Cleanup
Use when disk space is low, AI tool caches are bloated, or worktrees need cleanup.
Do NOT use for project structure issues (use /organize) or pre-merge worktree review (use /merge-review).
Orientation
Use when: cross-drive storage audit -- finds orphaned repos, stale branches, and large directories across all drives. Don't use when: auditing project infrastructure only (use /infra-audit); cleaning a specific directory (use Bash directly).
Invocation Forms
/houseclean # Full audit — all phases
/houseclean --quick # Drive survey + quick wins only (no deep scan)
/houseclean --worktrees # Orphaned worktree audit only
/houseclean --ai-tools # AI tool cache audit only
/houseclean --projects # Project artifact scan only (node_modules, .venv, etc.)
/houseclean --migrate X # Migration instructions for a specific tool (ollama, gemini, npm, cursor)
Protocol
Phase 1: Drive Survey
Windows (PowerShell):
Get-PSDrive -PSProvider FileSystem | Select-Object Name, Used, Free, Root | Format-Table -AutoSize
Present as a table with Drive, Total, Used, Free, Label columns.
Thresholds: C: free < 5 GB → CRITICAL. C: free < 20 GB → WARNING. Store which drives have free space — these are migration targets.
Phase 2: C Drive Hot Spots
Windows (PowerShell):
Get-ChildItem "C:\Users\$env:USERNAME" -Directory -ErrorAction SilentlyContinue |
ForEach-Object {
$s = (Get-ChildItem $_.FullName -Recurse -ErrorAction SilentlyContinue |
Measure-Object -Property Length -Sum).Sum
[PSCustomObject]@{ GB = [math]::Round($s/1GB,2); Path = $_.Name }
} | Sort-Object GB -Descending | Select-Object -First 15 | Format-Table -AutoSize
Tag each entry:
- AI-tool-data —
.ollama,.gemini,.cursor,.windsurf,.codex,.continue - IDE-cache —
.vscode,.idea,AppData\Local\JetBrains - Package-cache —
AppData\Local\npm-cache,AppData\Local\pip\cache,.gradle,.m2 - Conversation-history —
.claude\projects - Projects —
Desktop,Documents, user project directories - System —
AppData\Local\Microsoft,AppData\Roaming
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 2cb2bffd5e39
- 1mo ago First seen · 257 lines · 89 tokens per session scan A 6aa33d11ef1a
houseclean is a skill published in the GitHub repository SethGammon/Citadel (927 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 2,402 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
zapier-explore
Explore what Zapier MCP can do for the user — interview them about their role and the apps they live in, suggest specific use cases as on-demand prompts, then walk them through enabling the actions to make those use cases real. The natural next step after zapier-demo. Use when the user asks "what else can Zapier do…
compass
Open Spacedock Compass, the local dashboard of what your coding-agent sessions are doing: sessions, subagents, progress and drift. Use when the user wants to see, monitor or check on agent sessions, or asks to open Compass.
handoff
Use when work reaches a session boundary or the user asks to hand off, delegate, or get a clipboard-ready prompt. Mode brief packages continuity; mode prompt builds the delegation prompt.
askme
Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via /askme.
tmux-layout
Use this skill when the operator wants a prepared tmux visualization layout for the session's side-channels (STATE.md tail, CI-watch, events.jsonl tail). Renders a 4-pane default layout or debug layout. Read-only side-channel observability — the coordinator chat stays in the operator's original terminal. Trigger…
slicing-code-context
Use when an exact symbol, path, entrypoint, or line range can bound a focused code question or patch proposal under a fixed source budget. Not for source changes or broad repository exploration.