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 saajunaid/caddis-plugin --skill safe-cleanupgit clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/safe-cleanup)<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/safe-cleanup"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/safe-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/saajunaid/caddis-plugin/safe-cleanup"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/safe-cleanup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00054 | $0.01717 |
| Opus 5.5 | $0.00022 | $0.00687 |
| Sonnet 5.5 | $0.00011 | $0.00343 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
safe-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 19d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Cleanup
Overview
Cleanup looks like the safest thing you do all day. It is the most destructive.
This skill exists because of a real incident: an agent created 31 directory junctions from throwaway worktrees into live repositories, unlinked them, saw "31 unlinked, 0 failed", then recursively deleted the parent. A junction it had never seen survived the scan, the delete followed it, and five repositories' development environments were destroyed. Every verification afterwards said "intact", because the verification was wrong too.
Two hours of repair. None of it would have happened with the rules below.
The one-paragraph version
On Windows, Remove-Item -Recurse follows junctions and deletes their
targets. Enumerating with -ErrorAction SilentlyContinue hides the ones you
cannot read. And after the damage, pip check, pip list and file counts all
report success, because metadata survives while package files do not. So: never
link into somewhere real, never recurse through a link, prefer rename over
delete, and verify by using the thing rather than counting it.
RULE 1 - Prefer rename over delete
Rename is atomic. Recursive delete is not: it can fail half way and leave a directory that looks present and is unusable.
Rename-Item -Path $target -NewName ".broken-$(Get-Date -Format 'yyyyMMdd-HHmmss')"
In the incident, a venv holding _greenlet.cp314-win_amd64.pyd open refused to
delete but renamed fine. Had the delete been retried or forced, it would
have half-emptied the directory.
Rename first, build fresh alongside, delete the old copy later when nothing holds it. Disk is cheap. An environment nobody can recover is not.
RULE 2 - Never recurse a delete through a reparse point
Junctions and symlinks are transparent to Remove-Item -Recurse. Deleting a
folder that contains a link to C:\live\thing deletes the contents of
C:\live\thing.
Check first, and fail if the check itself cannot complete:
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.
- 19d ago Changed · -29 tokens per session 4282909a2873
- 1mo ago First seen · 177 lines · 83 tokens per session scan A ba7dadd44e2b
safe-cleanup is a skill published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 1,717 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
workflow-helper
Guidance for creating, managing and executing workflow automations that chain multiple tools and agents together. Use when the user asks about building, listing, running or composing workflows and automated task pipelines.
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
kb-setup
Set up, initialize, or configure the local markdown knowledge base for a project. Use when the user says "set up the knowledge base", "init the KB", "configure the markdown KB", "index my docs", "add a doc source to the KB", or wants the project's markdown searchable by kb search. Wraps kb init end-to-end through kb…
goga-review-plan
Verify execution plan completeness and correctness.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-discover
Interview the user relentlessly about a decision until every branch of the design tree is resolved, then record the result as a short ADR.