skillit-cli-docs

skillit-cli-docs is a skill for Claude Code, Codex from pradeepmouli/skillit. It costs 32 tokens per session (420 once invoked), scanned A, original, MIT.

A set of documentation rules for command-line programs built with Commander, a TypeScript and JavaScript library for defining terminal commands. It explains how to document commands, options, arguments, usage examples, and configuration links.

In plain words
What is it for?
Use it when improving Commander descriptions, help text, positional argument documentation, option descriptions, environment-variable notes, or routing guidance.
Why use it?
It helps generated agent skills explain a command-line tool accurately, including when a command should or should not be used.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when improving Commander descriptions, help text, positional argument documentation, option descriptions, environment-variable notes, or routing guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pradeepmouli/skillit/skillit-cli-docs
Install

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.

Any agent
npx skills add pradeepmouli/skillit --skill skillit-cli-docs
Clone the repo
git clone --depth 1 https://github.com/pradeepmouli/skillit

Made for: Claude Code, Codex.

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 skillit-cli-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/pradeepmouli/skillit/skillit-cli-docs/github.svg)](https://agentmods.dev/skills/pradeepmouli/skillit/skillit-cli-docs)
Your own site
<a href="https://agentmods.dev/skills/pradeepmouli/skillit/skillit-cli-docs"><img src="https://agentmods.dev/badge/skills/pradeepmouli/skillit/skillit-cli-docs/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 skillit-cli-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/pradeepmouli/skillit/skillit-cli-docs"><img src="https://agentmods.dev/badge/skills/pradeepmouli/skillit/skillit-cli-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 420 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 $0.00032 $0.00420
Opus 5.5 $0.00013 $0.00168
Sonnet 5.5 $0.00006 $0.00084
Haiku 4.5 $0.00003 $0.00042

Measured 2mo ago against content hash 228345a98dc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skillit-cli-docs 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 2mo 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.

packages/cli/skills/skillit-cli-docs/SKILL.md · 49 lines

What it actually says

CLI Documentation Conventions

Use this skill when documenting command-line programs for @skillit/cli.

Focus Areas

  • .description() text on commands and subcommands
  • .option() and --help descriptions for every flag
  • .argument() descriptions for positional inputs
  • .usage() strings and example help text
  • Environment-variable documentation and config-surface JSDoc correlation

Routing Tags via Option Interfaces

For routing tags (@useWhen, @avoidWhen, @never), add them as JSDoc on a <PascalCommandName>Options interface in a TypeScript source file. The interface needs no properties — only the JSDoc block matters:

/**
 * @useWhen - Server advertises callHierarchyProvider capability
 * @avoidWhen - Server doesn't support call hierarchy; lsproxy will error
 * @never - NEVER invoke without verifying server supports this capability. Fix: check --help output or use `lsproxy call` to probe the server first
 */
interface CallHierarchyOptions {}

CliRefineSource discovers these interfaces via the source glob (**/*.ts) and correlates their tags onto the corresponding command in the generated skill. Create one per command that needs routing guidance; the filename is arbitrary (e.g. src/command-options.ts). After adding the interface, re-run skillit gen to regenerate — resolveTargetLocation will now resolve and skillit refine can write tags into the interface directly.

Fix Patterns

  • Describe command intent in one sentence, not just the verb
  • Explain what each option changes in behavior
  • Document positional arguments with expected format or values
  • Mention env vars explicitly when an option supports them
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. 2mo ago First seen · 49 lines · 32 tokens per session scan A 228345a98dc2

Subscribe to this mod's changes

skillit-cli-docs is a skill published in the GitHub repository pradeepmouli/skillit (7 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 420 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.

Related

skillit-cli-docs compared with skills from other repositories

skillit-cli-docs next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skillit-cli-docspradeepmouli/skillitSkill74d agoMITA32Claude Code, Codex
releaseAterDev/Perigon.CLISkill544d agoApache-2.0A34Claude Code, Codex
docsAterDev/Perigon.CLISkill544d agoApache-2.0A67Claude Code, Codex
blazorAterDev/Perigon.CLISkill544d agoApache-2.0A45Claude Code, Codex
cliAterDev/Perigon.CLISkill544d agoApache-2.0A52Claude Code, Codex
codegenAterDev/Perigon.CLISkill544d agoApache-2.0A53Claude Code, Codex
dotnetAterDev/Perigon.CLISkill544d agoApache-2.0A61Claude Code, Codex