Borrowing it
Nothing to install: this file belongs to AmineDjeghri/personal-os-setup. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AmineDjeghri/personal-os-setup/main/.claude/skills/add-system-action/SKILL.mdgit clone --depth 1 https://github.com/AmineDjeghri/personal-os-setupWrote 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/aminedjeghri/personal-os-setup/add-system-action)<a href="https://agentmods.dev/skills/aminedjeghri/personal-os-setup/add-system-action"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/add-system-action/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/aminedjeghri/personal-os-setup/add-system-action"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/add-system-action.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 | $0.00078 | $0.01258 |
| Opus 5 | $0.00039 | $0.00629 |
| Sonnet 5 | $0.00016 | $0.00252 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
add-system-action 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 11d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a system action or package manager backend
This repo's TUI is entirely data-driven from src/personal_os_setup/tasks/factory.py::get_system_action_sections(). Never wire a button directly in frontend/app.py — add it to a section builder in factory.py instead. The frontend renders whatever sections/actions the factory returns generically (one TabPane per section, one Button per action), except for two special-cased sections it knows by name: "Sync dotfiles" (renders the chezmoi tree/toolbar) and "🚀 Start" (renders the onboarding markdown before the doc-link buttons).
For anything involving the chezmoi source tree itself (config/chezmoi/) — adding a run_* script, or explaining why a synced file's companion script didn't fire — see [[chezmoi-scripts]] first; the dotfiles tree's targeted-apply scoping is easy to get wrong.
⚠️ Every SystemAction.run you write or edit here is a real system-mutating command (installs a package, edits/overwrites a config file, changes the default shell, touches drivers, etc.) once a user clicks it in the running app. That's expected — it's the app's whole purpose — but when you (as the coding agent) are implementing/testing one of these, never invoke it against the real host yourself to "check it works." Read the code, run it through the unit-test mocks (see [[run-tests]]), and if you genuinely need to exercise the real command, confirm the exact command with the user first. See CLAUDE.md § "Safety: always confirm before system-mutating actions".
Adding a new action to an existing section
- Find the right per-domain builder function in
factory.py(e.g._dotfiles_section,_system_section,_wsl_section) — sections are independently unit-tested intests/unit/test_factory.py, one test class per section. - Append a
SystemAction(...)to that builder's returned list. Fields available:label(button text),run: Callable[[], TaskResult],run_with_prompt/prompt_label/prompt_initial(for free-text input actions),confirm/confirm_message(for destructive actions),backup_target: Path | None(file gets copied with a timestamp suffix beforerunexecutes),group: str | None(adjacent actions sharing agrouprender on one row). - The actual logic (
runcallable) lives intasks/system/<domain>.py, not infactory.py—factory.pyonly assemblesSystemActions and returnsTaskResults from imported functions. - Add/extend a test in
tests/unit/test_factory.pyusing the existing_actions_in(system, distro, section_name)/_action_in(...)helpers — these callget_system_action_sectionsdirectly, no App instantiation needed.
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.
- 11d ago First seen · 39 lines · 78 tokens per session scan A 5935ec78ce9b
add-system-action is a skill published in the GitHub repository AmineDjeghri/personal-os-setup (602 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 1,258 once invoked, about $0.0004 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.
Other skills, from other repositories
hula-skill
HuLa project skill for frontend (Vue 3 + Vite + UnoCSS + Naive UI/Vant), backend (Tauri v2 + Rust + SeaORM/SQLite), full-stack flows, and build/release work. Use when the user mentions hula or HuLa or requests changes in this repository; after triggering, ask which scope (frontend/backend/fullstack/build-release) to…
microsoft-powertoys
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize Microsoft PowerToys, FancyZones, PowerToys Run, Keyboard Manager, Awake, and settings.json automation.
eartrumpet
Inspect and route per-application audio with EarTrumpet, WASAPI, and pycaw; troubleshoot audio sessions and output devices.
flow-launcher
Build Flow Launcher plugins with C# or Python JSON-RPC, configure plugin manifests, and integrate Everything search.
wsl-bash-crlf-or-tempfile
When a Windows shell (PowerShell/cmd) feeds a bash script into WSL, CRLF line endings can corrupt the first shell builtin; force LF or pipe via a temp file.
wsl-networking-mode-dns-fallback
When WSL's mirrored networking fails and falls back to "None", plus /etc/wsl.conf has generateResolvConf=false, the distro has no DNS; fix both layers.