agentmods.dev

launch-store: Skill for Claude Code

.claude/skills/add-a-command/SKILL.md

add-a-command is a skill for Claude Code from YosefHayim/launch-store. It costs 34 tokens per session (278 once invoked), scanned A, original, MIT.

A procedure for adding a top-level command or subcommand to the launch CLI, a command-line tool. It keeps command wiring thin, places business logic in the core code, and regenerates command documentation.

In plain words
What is it for?
Use it when adding or changing launch commands, fixing documentation-check failures caused by the CLI surface, and adding the related tests.
Why use it?
It prevents CLI changes from being put in the wrong layer or leaving generated documentation out of sync.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions AGENTS.md.

This is YosefHayim/launch-store's own configuration. It tells Claude Code how to work on launch-store 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 launch-store configures →

not rated 12repo +1 changed 1mo ago A scan 34 tokens original MIT
View source ↗ YosefHayim/launch-store npmjs.com
Reuse

Borrowing it

Nothing to install: this file belongs to YosefHayim/launch-store. 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/YosefHayim/launch-store/main/.claude/skills/add-a-command/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/YosefHayim/launch-store

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-a-command

README.md
[![agentmods](https://agentmods.dev/badge/skills/yosefhayim/launch-store/add-a-command/github.svg)](https://agentmods.dev/skills/yosefhayim/launch-store/add-a-command)
Your own site
<a href="https://agentmods.dev/skills/yosefhayim/launch-store/add-a-command"><img src="https://agentmods.dev/badge/skills/yosefhayim/launch-store/add-a-command/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-a-command

Your own site · 80×15
<a href="https://agentmods.dev/skills/yosefhayim/launch-store/add-a-command"><img src="https://agentmods.dev/badge/skills/yosefhayim/launch-store/add-a-command.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 278 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.
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 $0.00034 $0.00278
Opus 5.5 $0.00014 $0.00111
Sonnet 5.5 $0.00007 $0.00056
Haiku 4.5 $0.00003 $0.00028

Measured 1mo ago against content hash f15b6b63b5e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-a-command 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 1mo 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-a-command/SKILL.md · 23 lines

What it actually says

Add a launch CLI command

Use this when

  • adding a new launch <command> or subcommand
  • a docs:check failure after changing the CLI surface

Steps

  1. Add the command as thin commander wiring in src/cli/commands/ and register its register*Command in src/cli/program.ts's buildProgram(). Keep domain logic in src/core, not the CLI layer.
  2. Run pnpm docs:gen - it introspects buildProgram() and regenerates llms.txt, the README stats badges, and the committed .cursor/rules / .claude/skills.
  3. Commit the regenerated files; pnpm docs:check (CI) fails if they drift.
  4. Add a *.test.ts beside the new logic, then run the gate.

The docs are generated from the live buildProgram() in src/cli/program.ts, so a new command surfaces in the reference automatically once you run docs:gen - never hand-edit the generated files.

See AGENTS.md.

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. 1mo ago Changed f15b6b63b5e0
  2. 2mo ago First seen · 23 lines · 34 tokens per session scan A 0ec1b517a51e

Subscribe to this mod's changes

add-a-command is a skill published in the GitHub repository YosefHayim/launch-store (12 stars, last pushed 8d ago), licensed MIT. It adds 34 tokens to every session and 278 once invoked, about $0.0001 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 2026-08-31.

CI and CDandroidapp-store-connectclicode-signingexpoios
Related

add-a-command compared with skills from other repositories

add-a-command next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
add-a-commandYosefHayim/launch-storeSkill128d agoMITA34Claude Code
uniwinduni-stack/uniwindSkill1.7kyesterdayMITA130Claude Code, Codex
flutterericrisco/rsc-harnessSkill5032d agoMITA91Claude Code, Codex
react-nativeericrisco/rsc-harnessSkill5032d agoMITA90Claude Code, Codex
migrate-nativewind-to-uniwinduni-stack/uniwindSkill1.7kyesterdayMITC82Claude Code, Codex
working-with-lacquerpatrickserrano/lacquerSkill54d agoMITA35Claude Code, Codex
github-ci-fixpatrickserrano/lacquerSkill54d agoMITA27Claude Code, Codex