What is paseo-agent-cleanup?

A safety-focused tool for previewing and archiving explicitly selected Paseo agents or clearly disposable test sessions. It treats an ordinary idle agent as resumable and does not delete, stop, or kill agents or workspaces.

Use it to preview cleanup candidates and archive agents identified by an explicit ID, user-supplied pattern, or clear temporary, test, fixture, smoke, or validation marker.

It reduces clutter without accidentally removing sessions that may still contain useful work.

paseo-agent-cleanup — Skill for Claude Code and Codex by wilgon456

Install

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.

Any agent

npx skills add wilgon456/Paseobility --skill paseo-agent-cleanup

Clone the repo

git clone --depth 1 https://github.com/wilgon456/Paseobility

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wilgon456/paseobility/paseo-agent-cleanup/github.svg)](https://agentmods.dev/skills/wilgon456/paseobility/paseo-agent-cleanup)

Your own site

<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.

Your own site · 80×15

<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>

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,828 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.01828
Opus 5	$0.00054	$0.00914
Sonnet 5	$0.00022	$0.00366
Haiku 4.5	$0.00011	$0.00183

Measured 10d ago against content hash 201fe46925ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/agent-cleanup.js, scripts/agent-cleanup.test.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/paseo-agent-cleanup/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paseo Agent Cleanup

This skill reduces Paseo list clutter without treating a normal idle session as disposable. A bare invocation only previews. Agent archive is limited to an explicit ID, a user-supplied pattern, or a clear disposable/test/validation marker. Workspace archive always requires an explicit workspace ID and --archive --yes.

Core rules

Treat idle as a normal resumable state, not as permission to archive.
Default to dry-run. Never archive every inactive agent by default.
--auto may archive only inactive agents selected by one of these signals:
- explicit --agent <id>
- a user-supplied --pattern <regex>
- a clear disposable, fixture, smoke, temp, test, or validation marker
Never archive active agents, including running, initializing, working, active, starting, queued, pending, busy, executing, or in-progress.
Never delete, stop, interrupt, or kill agents or workspaces. Never remove lock files or restart the Paseo daemon as part of cleanup.
Archive workspaces only after the user explicitly approves the exact cleanup plan or supplies explicit workspace IDs with --archive --yes.
After every archive attempt, re-run paseo ls --json (or paseo workspace ls --json) and verify the archived record is no longer in the active listing.
Do not open timeline/history or resume an archived agent to verify cleanup. Those operations can acquire a native provider writer lock.
Paseo 0.6 archive JSON must acknowledge the exact record with { agentId|workspaceId, status: "archived", archivedAt }. Exit code 0 alone is not enough.
Treat an invalid archive acknowledgement, a command failure, or a record-removal verification failure as partial/failed cleanup and return non-zero.

Quick workflow

Preview the safe default candidates. This makes no changes:
```
node skills/paseo-agent-cleanup/scripts/agent-cleanup.js
```
Review paseo ls --json and choose an explicit agent ID or a bounded pattern whenever possible:

Read the full file on GitHub · 206 lines

Files

What ships with it

2 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.

Changes

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.

10d ago First seen · 206 lines · 108 tokens per session scan A 201fe46925ad

Subscribe to this mod's changes

paseo-agent-cleanup is a skill published in the GitHub repository wilgon456/Paseobility (19 stars, last pushed 14d ago), licensed MIT. It adds 108 tokens to every session and 1,828 once invoked, about $0.0005 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 2026-08-30.

Building agents Productivity

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…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

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.

pinchtab/pinchtab · 52 tokens

paseo-agent-cleanup