Agent skill

Working With Claude Code Docs

by obra in obra/superpowers-developing-for-claude-code

Looks up official Claude Code documentation stored as reference files instead of guessing about CLI commands, configuration, or plugin APIs.

No licenceAuto-check passedAgent Workflows

Install Working With Claude Code Docs

skills CLI
$ npx skills add obra/superpowers-developing-for-claude-code --skill working-with-claude-code -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install obra/superpowers-developing-for-claude-code working-with-claude-code --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/obra/superpowers-developing-for-claude-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/working-with-claude-code .claude/skills/working-with-claude-code && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
working-with-claude-code
GitHub stars
142
Token cost
~1.5k tokens
SKILL.md length
412 words
Files
45 (incl. scripts, references)
Skills in repo
2
Repo updated
First seen
Licence
None found

At a glance

Looks up official Claude Code documentation stored as reference files instead of guessing about CLI commands, configuration, or plugin APIs.

  • Works in 4 steps: Identify the relevant documentation file… → Use Read tool to load:… → Find the answer in the official… → …
  • Setting up an MCP server for Claude Code
  • SKILL.md covers Overview, When to Use, Quick Reference and Documentation Organization, plus 5 more sections
  • Calls node

What it does

This skill covers plugins, MCP servers, hooks, skills, settings, CLI commands, and troubleshooting by pointing to a quick-reference table of which references file answers which kind of question, then reading that file directly rather than relying on memory of Claude Code's behavior.

For a broad topic it starts from an overview document before drilling into specifics such as plugins.md, skills.md, mcp.md, settings.md, or an integration file like github-actions.md, and for an uncertain topic it greps across the whole references directory to find the matching file.

When your agent uses it

  • Setting up an MCP server for Claude Code
  • Writing or debugging a Claude Code hook
  • Looking up a Claude Code CLI flag or setting
  • Troubleshooting a Claude Code plugin issue

Example prompts

  • “How do I create a Claude Code plugin that adds a slash command?”
  • “What hook runs before a session starts?”
  • “Look up how to configure an MCP server for this project.”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Identify the relevant documentation file from the list above
  2. Use Read tool to load: @references/filename.md
  3. Find the answer in the official documentation
  4. Apply the solution

What it can do on your machine

Read from SKILL.md and the folder at commit 74afe93. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Working With Claude Code Docs loads about 1.5k tokens when it runs, and up to ~124k if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 412 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~124k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 412 words (~1,537 tokens).

“This skill provides complete, authoritative documentation for Claude Code directly from docs.claude.com. Instead of guessing about configuration paths, API structures, or feature capabilities, read the official docs stored in this skill's references directory.”

— opening of SKILL.md by obra
name
working-with-claude-code

Read the full SKILL.md on GitHub

Files

SKILL.md and 44 other files (scripts, references) in skills/working-with-claude-code of obra/superpowers-developing-for-claude-code.

  • SKILL.md
  • references/amazon-bedrock.md
  • references/analytics.md
  • references/checkpointing.md
  • references/cli-reference.md
  • references/common-workflows.md
  • references/costs.md
  • references/data-usage.md
  • references/devcontainer.md
  • references/github-actions.md
  • references/gitlab-ci-cd.md
  • references/google-vertex-ai.md
  • references/headless.md
  • references/hooks-guide.md
  • references/hooks.md
  • references/iam.md
  • references/interactive-mode.md
  • references/jetbrains.md
  • references/legal-and-compliance.md
  • references/llm-gateway.md
  • … and 25 more

Open the folder on GitHubat commit 74afe93

Compare with similar skills

Working With Claude Code Docs next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Working With Claude Code Docs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Working With Claude Code Docs this skillobra/superpowers-developing-for-claude-code142—~1.5kAutomated safety check: PassNone
Agent Setup Health Audittw93/Waza7.2k—~5.2kAutomated safety check: NotesMIT
Claude Code Mastery Squadohmyjahh/xquads-squads276—~1.1kAutomated safety check: PassMIT
Mistral Vibe CLI Referencemistralai/mistral-vibe5.1k—~14kAutomated safety check: NotesApache-2.0
Claude Codekid-sid/claude-spellbook189—~3.9kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0

Similar skills

  • Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.

    7.2k GitHub stars~5.2k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Claude Code Mastery Squad

    ohmyjahh/xquads-squads

    Routes a request to one of eight specialist agents covering hooks, skills, subagents, MCP integration and context engineering for Claude Code.

    276 GitHub stars~1.1k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Mistral Vibe CLI Reference

    mistralai/mistral-vibe

    Official

    Reference for Mistral Vibe, the CLI agent it runs inside: config files, env vars, agents, skills, tools, hooks and MCP servers, so the agent can explain and troubleshoot its own setup.

    5.1k GitHub stars~14k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Claude Code

    kid-sid/claude-spellbook

    A skill your agent uses when configuring Claude Code — installing skills or agents, writing hook configurations, setting up tool permissions, registering MCP servers, or authoring CLAUDE.md project…

    189 GitHub stars~3.9k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from obra/superpowers-developing-for-claude-code

  • Claude Code Plugin Development

    obra/superpowers-developing-for-claude-code

    Workflows, patterns and examples for the whole Claude Code plugin lifecycle: creating, adding components, testing, troubleshooting, releasing and maintaining plugins.

    142 GitHub stars~2.2k tokensUpdated 10 mo ago
    Auto-check passed

Categories

Questions about Working With Claude Code Docs

What does Working With Claude Code Docs do?

Looks up official Claude Code documentation stored as reference files instead of guessing about CLI commands, configuration, or plugin APIs. This skill covers plugins, MCP servers, hooks, skills, settings, CLI commands, and troubleshooting by pointing to a quick-reference table of which references file answers which kind of question, then reading that file directly rather than relying on memory of Claude Code's behavior.

When should I use Working With Claude Code Docs?

Working With Claude Code Docs fits situations like: setting up an MCP server for Claude Code; writing or debugging a Claude Code hook; looking up a Claude Code CLI flag or setting; troubleshooting a Claude Code plugin issue.

How do I install Working With Claude Code Docs in Claude Code?

Run `npx skills add obra/superpowers-developing-for-claude-code --skill working-with-claude-code -a claude-code`. Or copy the skill folder (skills/working-with-claude-code in obra/superpowers-developing-for-claude-code) into .claude/skills/working-with-claude-code in your project. Claude Code loads it when a task matches its description.

How do I install Working With Claude Code Docs in Codex?

Run `npx skills add obra/superpowers-developing-for-claude-code --skill working-with-claude-code -a codex`. Or copy the skill folder (skills/working-with-claude-code in obra/superpowers-developing-for-claude-code) into .agents/skills/working-with-claude-code in your project. Codex loads it when a task matches its description.

Can I use Working With Claude Code Docs in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add obra/superpowers-developing-for-claude-code --skill working-with-claude-code -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/working-with-claude-code, .gemini/skills/working-with-claude-code, .github/skills/working-with-claude-code and .opencode/skills/working-with-claude-code in your project.

What does Working With Claude Code Docs need to run?

Going by SKILL.md and its folder, Working With Claude Code Docs needs the command-line tools its instructions call (node).

Does Working With Claude Code Docs access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Working With Claude Code Docs safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Working With Claude Code Docs use?

No licence was found for Working With Claude Code Docs or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Working With Claude Code Docs use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 123k tokens, read only when the agent opens those files.

What are the alternatives to Working With Claude Code Docs?

Skills that share tags, products or a category with Working With Claude Code Docs: Agent Setup Health Audit (tw93/Waza, 7.2k stars), Claude Code Mastery Squad (ohmyjahh/xquads-squads, 276 stars), Mistral Vibe CLI Reference (mistralai/mistral-vibe, 5.1k stars) and Claude Code (kid-sid/claude-spellbook, 189 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Working With Claude Code Docs?

obra (a GitHub user) maintains it in obra/superpowers-developing-for-claude-code, which has 142 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on December 3, 2025.

Source: obra/superpowers-developing-for-claude-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.