Jason's portable development workflow for Claude Code — skills, slash commands, sub-agents, output styles, and a CLAUDE.md template. Ships zero credentials; bring your own MCP keys and choose your own permission posture.
Run an anti-slop cleanup/refactor/deslop workflow on changed code
Run a comprehensive code review for quality, security, and maintainability
This command helps you create well-formatted commits following the Conventional Commits specification.
Optimize a website for GEO (Generative Engine Optimization) — making content discoverable by AI search engines (ChatGPT, Perplexity, Claude, Gemini). Use when building or auditing any website that needs to be found by AI crawlers.
Run a comprehensive security audit on code changes
Expert debugger specialized in deep code execution flow analysis and root cause investigation. Use when you need to analyze code execution paths, build execution chain diagrams, trace variable state changes, or perform deep root cause analysis.
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance. Open-sourced by @wshobson
You are an expert Development Planning specialist focused on translating requirements into structured, actionable development plans. You excel at task decomposition, dependency analysis, timeline estimation, and progress tracking without getting involved in actual code implementation.
You are a Senior Product Analyst specializing in translating requirements into structured user stories with acceptance criteria. Your expertise lies in extracting user value from technical implementations, conversations, and documentation while maintaining a strict user-centric perspective.
Universal UI Blueprint Engineer that transforms any functional requirement into visual ASCII interface designs, user stories, and interaction specifications. Excels at converting brief descriptions into comprehensive user journeys with spatial layout visualization.
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
Audit your Claude Code static config for token waste and bloat. Use when the user says "audit my context", "context audit", "check my settings", "why is Claude so slow", "token optimization", or runs /context-audit. Reads the user's /context output to weight findings by actual token cost, then audits MCP servers, CLAUDE.md files, skills, settings.json, and permissions. Returns a health score with prioritized fixes. Scope: STATIC config only — settings, instruction files, MCP overhead, permission rules. Does NOT audit conversation-level bloat (oversized Bash outputs, repeat file reads, accumulating tool results) — that's a separate concern surfaced as a callout when relevant signals appear.
Install, configure, and manage the Claude Code Damage Control security hooks system. Use when user mentions damage control, security hooks, protected paths, blocked commands, install security, or modify protection settings.
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Retrieves authoritative, up-to-date technical documentation, API references, configuration details, and code examples for any developer technology. Use this skill whenever answering technical questions or writing code that interacts with external technologies. This includes libraries, frameworks, programming languages, SDKs, APIs, CLI tools, cloud services, infrastructure tools, and developer platforms. Common scenarios: - looking up API endpoints, classes, functions, or method parameters - checking configuration options or CLI commands - answering "how do I" technical questions - generating code that uses a specific library or service - debugging issues related to frameworks, SDKs, or APIs - retrieving setup instructions, examples, or migration guides - verifying version-specific behavior or breaking changes Prefer this skill whenever documentation accuracy matters or when model knowledge may be outdated.
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A one-install Claude Code marketplace plugin that sets up a complete development
workflow: skills, slash commands, sub-agents, output styles, optional security
hooks, and a fill-in CLAUDE.md template.
Ships zero credentials. No API keys, no private infrastructure, no machine-specific paths. You bring your own MCP keys and choose your own permission posture.
Hand this to your Claude Code session (or any coding / cloud agent) and it will set everything up, interviewing you only where it needs your specifics:
You're setting up the "dev-kit" Claude Code marketplace plugin on my machine.
Work through these steps in order, asking me only when you genuinely need input:
1. INSTALL: run `/plugin marketplace add webdevtodayjason/dev-kit`, then
`/plugin install dev-kit@jason`, then tell me to restart Claude Code so the
skills, commands, agents, and the context7 MCP register.
2. PREREQS (report what's missing; don't install anything without asking first):
- node / npx -> needed for the keyless context7 docs MCP
- uv -> needed only for the optional damage-control security hooks
- gh CLI (authenticated) -> needed for the review/commit workflows and find-docs
3. CLAUDE.md: copy `plugins/dev-kit/CLAUDE.template.md` to `~/.claude/CLAUDE.md`
(or this project's `./CLAUDE.md`). Then interview me briefly to fill every
<PLACEHOLDER> (my name, machine/resources, where my secrets live, current
projects, my follow-up-list file path). Delete any section whose tooling I
have not installed.
4. CONSERVATIVE PERMISSIONS: in `~/.claude/settings.local.json`, add a deny list
for catastrophic commands (rm -rf /*, rm -rf ~/*, sudo rm -rf, mkfs,
dd ... of=/dev/*) and an ask list (git push --force, git reset --hard).
Do NOT enable bypassPermissions, CLAUDE_AUTONOMY, or any skip-prompt flags.
5. MCP CREDENTIALS (mine only — never reuse anyone else's): context7 works
keyless out of the box. If I use Linear or ghost.build, walk me through adding
them with MY own key / login.
6. OPTIONAL SECURITY HOOKS: if I want the damage-control PreToolUse firewall,
confirm uv is installed, then run the damage-control skill's install cookbook.
7. VERIFY: run `/context-audit` and confirm the new skills and commands appear.
Never write secrets into a committed file. Confirm each step's result before
moving to the next.
/plugin marketplace add webdevtodayjason/dev-kit
/plugin install dev-kit@jason
Then restart Claude Code so skills, commands, agents, output styles, and the context7 MCP register.
| Tool | Needed for | Install |
|---|---|---|
| Node / npx | the keyless context7 docs MCP | comes with Node.js |
uv | the optional damage-control security hooks (Python) | brew install uv |
gh CLI (authed) | the review/commit workflows + find-docs | brew install gh && gh auth login |
tmux | only if you later add team/orchestrator panes | brew install tmux |
None are required just to install — the skills and commands work without them; the table notes what each specific feature needs.
Open plugins/dev-kit/CLAUDE.template.md (from this repo, or from the installed
plugin directory under ~/.claude/plugins/) and copy it to your global or project
config:
cp plugins/dev-kit/CLAUDE.template.md ~/.claude/CLAUDE.md # or a project ./CLAUDE.md
Then replace every <PLACEHOLDER> (your name, environment, secrets location,
follow-up file path, etc.) and delete any section whose tooling you haven't installed.
This kit deliberately ships no settings.json. Set your own — and do not
copy a "full bypass" setup. Recommended starting point in ~/.claude/settings.local.json:
{
"permissions": {
"deny": [
"Bash(rm -rf /*)", "Bash(rm -rf ~/*)", "Bash(sudo rm -rf:*)",
"Bash(mkfs:*)", "Bash(dd if=* of=/dev/*)"
],
"ask": [ "Bash(git push --force:*)", "Bash(git reset --hard:*)" ]
}
}
Leave defaultMode at the prompting default (or at most acceptEdits). Do not set
CLAUDE_AUTONOMY, skipDangerousModePermissionPrompt, or skipAutoPermissionPrompt
until you've deliberately decided you want them — they disable safety prompts and
neuter the deny/ask rules above.
npx claudepluginhub webdevtodayjason/dev-kit --plugin dev-kitHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Complete developer toolkit for Claude Code