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 lifedever/skills-plugin --skill mac-app-uninstallgit clone --depth 1 https://github.com/lifedever/skills-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/lifedever/skills-plugin/mac-app-uninstall)<a href="https://agentmods.dev/skills/lifedever/skills-plugin/mac-app-uninstall"><img src="https://agentmods.dev/badge/skills/lifedever/skills-plugin/mac-app-uninstall.svg" alt="Measured on agentmods" 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 | $0.00360 | $0.03194 |
| Opus 5 | $0.00180 | $0.01597 |
| Sonnet 5 | $0.00072 | $0.00639 |
| Haiku 4.5 | $0.00036 | $0.00319 |
Grade D, and why
mac-app-uninstall scanned grade D with 2 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 7d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
description: Browse installed macOS applications and uninstall any of them together with every leftover they left behind — a scriptable replacement for AppCleaner / CleanMyMac. Also use this to simply LIST what is instal Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
sudo rm -rf /Library/PrivilegedHelperTools/<label> How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mac-app-uninstall
Removes a macOS app and its leftovers, the way AppCleaner does — but with the reasoning visible and auditable at every step.
The bottom line: everything goes to the Trash, so any mistake can be undone. There is no permanent-delete path in this skill, by design. Never work around that with your own rm.
Iron rule: identify → scan → show the report → confirm → dry run → execute → verify.
Division of labour
You do the judgement, the scripts do the enforcement:
| You (the agent) | The scripts |
|---|---|
| Work out which app the user means — ask, never guess | Inventory installed apps and enumerate leftovers |
| Optionally hunt for extra leftovers by name (step 4) | Decide ownership when apps nest in each other's namespaces |
| Explain, summarise, get consent | Enforce the path allow-list, Apple/Setapp protection, Trash-only |
scan.sh deliberately does no fuzzy matching — it takes an exact bundle id, exact app name, or a path. Guessing is your job, because you can ask a clarifying question and it cannot.
Where output goes
Everything lands under ~/Downloads/mac-app-uninstall/:
apps-<ts>.md the installed-app inventory
<App>-<ts>/report.md scan report for one app
<App>-<ts>/manifest.tsv what uninstall.sh acts on
<App>-<ts>/result.md what was trashed + verification
One folder per uninstall, so a run's report, manifest and result stay together.
The generated files are written in Chinese and open automatically in Typora
(falling back to the system default). Set MAU_NO_OPEN=1 or pass --no-open to
suppress opening — do that when running several scans in a row, so the user isn't
buried in windows.
0. Pre-flight
/usr/bin/trash ships with macOS 14+. The scripts are pure base-system bash; nothing to install.
mole is optional — mo uninstall --list gives a JSON app inventory with a Homebrew/Setapp/App source field. Never use mo uninstall to remove anything: with an app argument it doesn't list what it will delete and it blocks on a [y/N] prompt, so there is nothing to audit.
What ships with it
6 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.
- 7d ago First seen · 231 lines · 360 tokens per session scan D c7dca04dfb1d
mac-app-uninstall is a skill published in the GitHub repository lifedever/skills-plugin (11 stars, last pushed 15d ago), licensed MIT. It adds 360 tokens to every session and 3,194 once invoked, about $0.0018 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). 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…
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.