Claude Code Slash Commands
57 production-ready slash commands for Claude Code, including multi-agent workflow orchestration and specialized tools.
- Source repo
- wshobson/commands
- Stars
- ★ 2.6k
- Last updated
- 18d ago
- License
- MIT
- FA score
- 36/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specificClaude Code
- Cost
- Free software; you pay for model usage
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A developer wants to implement a complete feature from scratch, using /workflows:feature-development to coordinate backend, frontend, and testing.
- Not a fit if
- Teams not using Claude Code; commands don't work in other AI coding tools
- Workflows needing instant responses; orchestration typically takes 30-90 seconds
- Enterprises requiring commercial support or an SLA; community-maintained only
- Source review
- 36/100 · Major gaps 8 safety controls not found
What does this agent do, and when should you use it?
This repository is a collection of production-ready slash commands for Claude Code, comprising 15 workflows and 42 tools that extend Claude Code through intelligent automation and multi-agent orchestration. Workflows such as feature-development, smart-fix, and tdd-cycle coordinate multiple specialized agents for complex cross-domain tasks, while tools like api-scaffold, security-scan, and docker-optimize provide focused utilities for specific development operations. Installation requires cloning the repository into ~/.claude and invoking commands with /workflows: or /tools: prefixes. It supports scenarios like feature development, debugging, security auditing, and test-driven development.
The collection runs Markdown files as slash commands within Claude Code. Workflows (feature-development, smart-fix, tdd-cycle) orchestrate multi-step processes by delegating to specialized agents like backend, frontend, testing, and deployment. Tools (api-scaffold, security-scan, docker-optimize) generate code, configuration, or reports; for example, api-scaffold creates REST endpoints, security-scan performs vulnerability scanning, and docker-optimize creates multi-stage Dockerfiles. Commands take user input via $ARGUMENTS placeholder and produce concrete artifacts for the current project. Workflows and tools are organized in workflows/ and tools/ directories.
- A developer wants to implement a complete feature from scratch, using /workflows:feature-development to coordinate backend, frontend, and testing.
- A team needs to audit OWASP Top 10 vulnerabilities, using /tools:security-scan to generate a vulnerability report with fixes.
- A developer wants to adopt test-driven development, using /workflows:tdd-cycle to automate the red-green-refactor loop.
- An operations engineer needs to generate Kubernetes configurations for a service, using /tools:k8s-manifest to create YAML manifests with best practices.
- A developer wants to optimize Docker images, using /tools:docker-optimize to reduce size by 50-90% with multi-stage builds.
How do you install or deploy this agent?
- Ensure Claude Code is installed and configured. 2. Open terminal and clone the repository into Claude's config directory: cd ~/.claude && git clone https://github.com/wshobson/commands.git 3. For the plugin marketplace alternative, run /plugin marketplace add https://github.com/wshobson/agents inside Claude Code and install collections.
How do you use this agent?
After installation, invoke commands with prefixes, e.g., /workflows:feature-development implement OAuth2 authentication or /tools:security-scan perform vulnerability assessment. To invoke without prefixes, copy files to root: cp tools/*.md . and cp workflows/*.md ., then use /api-scaffold create user management endpoints directly. Commands can be chained, e.g., run feature-development then security-scan.
What are this agent's strengths and limitations?
- Provides 57 production-ready commands covering development, security, operations, data, and more, ready to use.
- Workflows implement multi-agent orchestration, automatically assigning tasks to different specialized agents for complex cross-domain scenarios.
- Tool commands are optimized for specific tasks, such as security scanning with SAST/DAST and dependency audits.
- Includes complete test-driven development suite (tdd-red/green/refactor) and zero-downtime database migration strategies.
- Offers clear command selection guidelines and composition patterns to help users quickly find the right command.
- Depends on Claude Code-specific environment, not directly usable in other AI coding tools.
- Requires cloning the repository into ~/.claude and familiarity with command-line and Claude Code configuration.
- Workflows may take 30-90 seconds to execute, not suitable for rapid iteration or real-time response.
- No commercial support or SLA documented; relies on community maintenance.
- Compatibility with future Claude Code versions may vary; commands may need verification after upgrades.
How does this agent compare with similar options?
The repository offers an alternative installation via the plugin marketplace (https://github.com/wshobson/agents), which provides a cleaner plugin architecture with similar functionality, giving users a choice.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Claude Code Slash Commands This agent | 36 · Major gaps | Agent plugin / skillFree + model costs | ★ 2.6k | 18d ago | — | Claude Code |
| Bug Hunter | 79 · Good | Agent plugin / skillFree + model costs | ★ 526 | 2mo ago | JavaScript | Codex · Claude Code |
| Claude Forge | 48 · Major gaps | Agent plugin / skillFree + model costs | ★ 858 | 1mo ago | Shell | Claude Code |
| Pi Dynamic Workflows | 88 · Good | Agent plugin / skillFree + model costs | ★ 555 | 12d ago | TypeScript | — |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows the repository contains only README and LICENSE, with no actual command files or execution logic, so least privilege, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, rollback, and source attribution cannot be assessed. All trust criteria score 0 due to lack of evidence.
Self-consistency: README is internally consistent, with command lists and architecture descriptions matching, score 2. Dependency availability: Only mentions Claude Code and Git as system requirements, but no versions or verification, score 1. Failure messages: README provides some troubleshooting guidance, but no specific error handling for command execution failures, score 1.
Audience and scenarios: README details multiple usage scenarios and command selection guidelines, score 2. Capability boundaries: Distinguishes workflows and tools, explaining their purposes, score 2. Trigger precision: Command naming is clear, but no detailed argument validation or error handling, score 2. Environment fit: Provides installation and configuration instructions, but no compatibility notes for different OS or Claude Code versions, score 2.
Information architecture: README is well-structured with table of contents and categorization, score 2. Install notes: Provides installation steps, but no version requirements or dependency management, score 2. Naming stability: Command naming is consistent, but no version history, score 2. Examples and FAQ: Provides extensive examples, but lacks FAQ section, score 2. Known limitations: No explicit limitations listed, score 1. License: MIT license present, score 2. Versioning and changelog: No version numbers or changelog, score 0. Maintenance responsibility: No clear maintainer or contribution guidelines, score 1.
Output usability: README describes output types, but no actual output examples, score 2. Marginal value: Provides a rich command set, but no comparison with other tools, score 2. Cost-benefit: No performance or resource consumption data, score 1.
Claim traceability: Claims in README are not referenced to specific files or tests, score 1. Cross-source corroboration: No external verification, score 0. Fact-inference separation: Some content is inferential, not clearly distinguished, score 1.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- The repository contains only README and LICENSE, with no actual command files, so the actual behavior and security of the commands cannot be verified.
- Publisher identity is unverified; do not infer safety based on brand or reputation.
- Performance claims in README (e.g., docker-optimize reduces size by 50-90%) lack supporting evidence.