Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Delegate coding and file edits to Anthropic Claude Code CLI. An agent skill from taracodlabs/aiden.
Install Claude Code
$ npx skills add taracodlabs/aiden --skill claude-code -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install taracodlabs/aiden claude-code --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/taracodlabs/aiden.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claude-code .claude/skills/claude-code && rm -rf skills-srcUse ~/.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/
Install the "claude-code" agent skill from https://github.com/taracodlabs/aiden/tree/main/skills/claude-code into .claude/skills/claude-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/taracodlabs/aiden/tree/main/skills/claude-codeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add taracodlabs/aiden --skill claude-code -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install taracodlabs/aiden claude-code --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/taracodlabs/aiden.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/claude-code .agents/skills/claude-code && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "claude-code" agent skill from https://github.com/taracodlabs/aiden/tree/main/skills/claude-code into .agents/skills/claude-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add taracodlabs/aiden --skill claude-code -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install taracodlabs/aiden claude-code --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/taracodlabs/aiden.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/claude-code .cursor/skills/claude-code && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "claude-code" agent skill from https://github.com/taracodlabs/aiden/tree/main/skills/claude-code into .cursor/skills/claude-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/taracodlabs/aiden.git --path skills/claude-code--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add taracodlabs/aiden --skill claude-code -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install taracodlabs/aiden claude-code --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/taracodlabs/aiden.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/claude-code .gemini/skills/claude-code && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "claude-code" agent skill from https://github.com/taracodlabs/aiden/tree/main/skills/claude-code into .gemini/skills/claude-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install taracodlabs/aiden claude-codeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add taracodlabs/aiden --skill claude-code -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/taracodlabs/aiden.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/claude-code .github/skills/claude-code && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "claude-code" agent skill from https://github.com/taracodlabs/aiden/tree/main/skills/claude-code into .github/skills/claude-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add taracodlabs/aiden --skill claude-code -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install taracodlabs/aiden claude-code --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/taracodlabs/aiden.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/claude-code .opencode/skills/claude-code && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "claude-code" agent skill from https://github.com/taracodlabs/aiden/tree/main/skills/claude-code into .opencode/skills/claude-code/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
claude-code- GitHub stars
- 849
- Token cost
- ~895 tokens
- SKILL.md length
- 273 words
- Files
- 2
- Skills in repo
- 63
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Delegate coding and file edits to Anthropic Claude Code CLI. An agent skill from taracodlabs/aiden.
- Works in 7 steps: Install Claude Code → Run Claude Code on a task → Non-interactive (headless) mode → …
- Development work in your project
- SKILL.md covers When to Use, How to Use, Examples and Cautions
- Calls claude, npm and git; needs ANTHROPIC_API_KEY
What it does
Claude Code is an agent skill from taracodlabs/aiden. Delegate coding and file edits to Anthropic Claude Code CLI
Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `skill.json`).
It sits in Development. The repository describes itself as: Aiden — an autonomous AI agent and work engine built solo. It can operate your browser, terminal, files, apps, APIs, skills and tools, remember context, recover from failures… The licence is Apache-2.0.
When your agent uses it
- Development work in your project
Example prompts
- “/claude-code”
Requirements
- Node.js
- A credential in ANTHROPIC_API_KEY
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 3704204. 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
Shell commands in SKILL.md call:
claudenpmgit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
ANTHROPIC_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Claude Code loads about 895 tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 273 words of instructions outside code blocks.
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from taracodlabs/aiden at commit 3704204, republished under its Apache-2.0 licence (© taracodlabs). 273 words, ~895 tokens.
Download SKILL.mdSave it as
.claude/skills/claude-code/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- claude-code
- description
- Delegate coding and file edits to Anthropic Claude Code CLI
- category
- agent-bridge
- version
- 1.0.0
- origin
- aiden
- license
- Apache-2.0
- tags
- claude, anthropic, code, cli, agent-bridge, coding, delegation, agentic, pair-programming
Claude Code Agent Bridge
Delegate complex multi-file coding tasks, refactoring, and code review to Anthropic Claude Code CLI. Claude Code has deep IDE integration and can make targeted edits across an entire codebase.
When to Use
- Task requires deep multi-file refactoring beyond a single script
- User wants an expert code review with inline suggestions
- Task requires reading, understanding, and rewriting large codebases
- User wants to pair-program with an AI that can navigate projects
- Task requires complex TypeScript/Python/Rust code generation
How to Use
1. Install Claude Code
# Requires Node.js 18+
npm install -g @anthropic-ai/claude-code
# Verify installation
claude --version
# Authenticate (requires Anthropic API key)
$env:ANTHROPIC_API_KEY = "sk-ant-..."2. Run Claude Code on a task
# Navigate to the project
Set-Location "C:\Users\<you>\myproject"
# Run with a specific task
claude "Refactor the authentication module to use JWT tokens instead of sessions"3. Non-interactive (headless) mode
# Run a specific task non-interactively (for automation)
claude --print "Review the function in src/utils.ts and suggest improvements"
# Pipe output to a file
claude --print "Generate TypeScript interfaces for this JSON schema" | Out-File types.ts4. Run Claude Code on a specific file
# Ask Claude to work on a specific file
claude "Fix all TypeScript type errors in src/components/Dashboard.tsx"
# With additional context
claude "The function processPayment in src/payments.ts fails when amount is 0. Fix it."5. Run in print mode to get a response without editing files
# Get a code review without applying changes
$review = claude --print "Review src/api.ts for security vulnerabilities and anti-patterns"
Write-Host $review6. Delegate a complex refactoring task
# Multi-step task with context
$task = @"
Refactor the codebase to:
1. Extract all database queries from controllers into a repository layer
2. Add TypeScript types for all repository methods
3. Update all tests to use the new repository interfaces
"@
claude $task7. Run on a different directory
claude --directory "C:\Users\<you>\other-project" "Add error handling to all async functions"Examples
"Refactor my Express API to use async/await everywhere"
→ Navigate to the project directory and use step 2: claude "Refactor all callback-based Express route handlers to use async/await with proper error handling".
"Review my authentication code for security issues"
→ Use step 5 with --print to get a review without applying changes.
"Generate TypeScript interfaces for my API response types" → Use step 3 in headless mode, pipe output to a types file.
Cautions
- Claude Code applies edits directly to files — review changes with
git diffafter each session ANTHROPIC_API_KEYmust be set — Claude Code bills against the Anthropic API- Headless mode (
--print) does not apply changes — it only returns text - For large codebases, scope the task to a specific module or file to avoid context overflow
- Always commit or stash changes before running Claude Code on a large task, so you can revert if needed
© taracodlabs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/claude-code of taracodlabs/aiden.
- SKILL.md
- skill.json
Open the folder on GitHubat commit 3704204
Compare with similar skills
Claude Code 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Claude Code this skilltaracodlabs/aiden | 849 | — | ~895 | Automated safety check: Pass | Apache-2.0 | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 24 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Greplooponyx-dot-app/onyx | 32k | 4 repos | ~3.3k | Automated safety check: Pass | MIT |
Similar skills
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
Guidelines
akash-network/node
Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.
More from taracodlabs/aiden
All 63 skills in this repoGoogle Flights Search
taracodlabs/aiden
Searches Google Flights for prices, schedules and availability through browser automation with URL-based queries, and stops short of booking.
OpenAI Codex CLI Bridge
taracodlabs/aiden
Delegates code generation, editing and explanation tasks to the OpenAI Codex CLI, with commands for interactive, auto-edit, question-only and model-specific runs.
Google Hotels Search
taracodlabs/aiden
Searches Google Hotels through the agent-browser tool for prices, ratings, amenities and availability, building a search URL from the location and dates and reporting a results table.
HTML Architecture Diagram Maker
taracodlabs/aiden
Generates dark-themed architecture, component, data-flow and network diagrams as self-contained HTML and SVG files that open in any browser.
Indian Broker Portfolio Bridge
taracodlabs/aiden
Aggregates holdings across Zerodha, Upstox and Angel One and normalizes order parameters into one format, with confirmation required before any routing.
arXiv Paper Search
taracodlabs/aiden
Searches arXiv by keyword, category, author or paper ID through its public API and downloads PDFs, with no API key needed.
Related
Categories
Questions about Claude Code
What does Claude Code do?
Delegate coding and file edits to Anthropic Claude Code CLI. An agent skill from taracodlabs/aiden. Claude Code is an agent skill from taracodlabs/aiden.
When should I use Claude Code?
Claude Code fits situations like: development work in your project.
How do I install Claude Code in Claude Code?
Run `npx skills add taracodlabs/aiden --skill claude-code -a claude-code`. Or copy the skill folder (skills/claude-code in taracodlabs/aiden) into .claude/skills/claude-code in your project. Claude Code loads it when a task matches its description.
How do I install Claude Code in Codex?
Run `npx skills add taracodlabs/aiden --skill claude-code -a codex`. Or copy the skill folder (skills/claude-code in taracodlabs/aiden) into .agents/skills/claude-code in your project. Codex loads it when a task matches its description.
Can I use Claude Code 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 taracodlabs/aiden --skill 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/claude-code, .gemini/skills/claude-code, .github/skills/claude-code and .opencode/skills/claude-code in your project.
What does Claude Code need to run?
Going by SKILL.md and its folder, Claude Code needs the command-line tools its instructions call (claude, npm and git) and credentials named ANTHROPIC_API_KEY. Our summary lists: Node.js; A credential in ANTHROPIC_API_KEY.
Does Claude Code access the network?
SKILL.md contains no URLs. Its commands use npm and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Claude Code 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. Review the folder before installing.
What licence does Claude Code use?
Claude Code is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Claude Code use?
About 895 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Claude Code?
Skills that share tags, products or a category with Claude Code: Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars) and Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Claude Code?
taracodlabs (a GitHub organization) maintains it in taracodlabs/aiden, which has 849 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on September 13, 2026.
Source: taracodlabs/aiden on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.