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 wilgon456/Paseobility --skill paseo-agent-cleanupgit clone --depth 1 https://github.com/wilgon456/PaseobilityWrote 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/wilgon456/paseobility/paseo-agent-cleanup)<a href="https://agentmods.dev/skills/wilgon456/paseobility/paseo-agent-cleanup"><img src="https://agentmods.dev/badge/skills/wilgon456/paseobility/paseo-agent-cleanup/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/wilgon456/paseobility/paseo-agent-cleanup"><img src="https://agentmods.dev/badge/skills/wilgon456/paseobility/paseo-agent-cleanup.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 | $0.00108 | $0.00656 |
| Opus 5.5 | $0.00043 | $0.00262 |
| Sonnet 5.5 | $0.00022 | $0.00131 |
| Haiku 4.5 | $0.00011 | $0.00066 |
Grade A, and why
paseo-agent-cleanup 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 8d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paseo Agent Cleanup
Archive agents the user selected or that are clearly disposable. Agent archive
is a soft delete: the record stays in Paseo (paseo agent ls -a). Run the
bundled helper by its absolute path:
node "<skill-dir>/scripts/agent-cleanup.js" --json # preview (default)
node "<skill-dir>/scripts/agent-cleanup.js" --agent <full-id> --archive
node "<skill-dir>/scripts/agent-cleanup.js" --pattern '<regex>' --archive
node "<skill-dir>/scripts/agent-cleanup.js" --auto # disposable markers only
node "<skill-dir>/scripts/agent-cleanup.js" --workspace <full-id> --archive --yes
When the user names the agents or the pattern, archive directly; preview only
when the selection is unclear. --auto picks agents with test, fixture,
validation, temp or similar markers in their name, cwd or project.
Guards (enforced by the helper)
- Only
idle,errororclosedagents can be archived. Running, initializing and unknown states stay protected, even with an exact ID. - Pending permissions or unfinished attention block archive.
- Idle alone never selects an agent; ordinary idle agents stay resumable.
- Workspaces need an exact ID and
--yes: archive takes their agents and terminals and may remove the managed worktree. Any active or permission-pending child blocks it. A test-like title alone does not authorize a workspace. - Ambiguous short IDs are refused; use full IDs.
- Never use delete, stop, kill, restart, history, timeline or resume for cleanup.
Each archive gets a fresh precheck and a postcheck against a complete paginated snapshot from the installed Paseo client. An unacknowledged or unverified archive halts the rest; inspect fresh state instead of retrying blindly. The checks narrow but do not close the read-to-archive race, so do not call them atomic.
Runtime and fallback
Needs Node and an installed Paseo desktop app or npm CLI. For a custom install,
set both PASEO_CLEANUP_CLIENT_MODULE and PASEO_CLEANUP_NODE. If the client
cannot be loaded, use the MCP flow in references/cleanup.md
with the same guards.
What ships with it
5 files 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.
- 8d ago Changed · -19 lines a5d8aa2b6682
- 15d ago Changed · -126 lines 7d38ddccd7e7
- 1mo ago Changed 36d93fd23bd3
- 1mo ago First seen · 206 lines · 108 tokens per session scan A 201fe46925ad
paseo-agent-cleanup is a skill published in the GitHub repository wilgon456/Paseobility (25 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 656 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.