personal-os-setup: Skill for Claude Code

.claude/skills/add-system-action/SKILL.md

add-system-action is a skill for Claude Code from AmineDjeghri/personal-os-setup. It costs 78 tokens per session (1,258 once invoked), scanned A, original, MIT.

A guide for adding buttons, actions, tabs, or package-manager support to the project’s text-based user interface. It explains the code patterns used to expose these actions to users.

In plain words
What is it for?
Use it to add a setup button, create a new interface section, support another package manager, or write the required tests for such a change.
Why use it?
It helps new actions appear through the project’s existing data-driven interface instead of being wired into the wrong file. It also highlights that these actions can change system settings or install software.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is AmineDjeghri/personal-os-setup's own configuration. It tells Claude Code how to work on personal-os-setup itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything personal-os-setup configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/AmineDjeghri/personal-os-setup/main/.claude/skills/add-system-action/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AmineDjeghri/personal-os-setup

Made for: Claude Code.

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.

agentmods badge for add-system-action

README.md
[![agentmods](https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/add-system-action/github.svg)](https://agentmods.dev/skills/aminedjeghri/personal-os-setup/add-system-action)
Your own site
<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.

agentmods 80×15 button for add-system-action

Your own site · 80×15
<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>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,258 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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 5935ec78ce9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.claude/skills/add-system-action/SKILL.md · 39 lines

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

  1. Find the right per-domain builder function in factory.py (e.g. _dotfiles_section, _system_section, _wsl_section) — sections are independently unit-tested in tests/unit/test_factory.py, one test class per section.
  2. 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 before run executes), group: str | None (adjacent actions sharing a group render on one row).
  3. The actual logic (run callable) lives in tasks/system/<domain>.py, not in factory.pyfactory.py only assembles SystemActions and returns TaskResults from imported functions.
  4. Add/extend a test in tests/unit/test_factory.py using the existing _actions_in(system, distro, section_name) / _action_in(...) helpers — these call get_system_action_sections directly, no App instantiation needed.

Read the full file on GitHub · 39 lines

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.

  1. 11d ago First seen · 39 lines · 78 tokens per session scan A 5935ec78ce9b

Subscribe to this mod's changes

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.