By ek33450505
Orchestrate multi-agent teams with curated specialist agents, hook-enforced quality gates, and SQLite observability for Claude Code — enabling parallel task execution, automated code review, security scanning, git workflow automation, and structured planning across large refactors or feature work.
Shell scripting specialist for CAST hook scripts, BATS tests, and automation scripts. Use when writing new hook scripts, BATS test suites, reviewing shell code for correctness, debugging hook behavior, or extending CAST automation. Knows CAST-specific conventions: exit codes, escape hatches, hookSpecificOutput JSON format, and CLAUDE_SUBPROCESS guard patterns.
Per-unit code-quality and security review of a single logical change mid-flight, any language. Use immediately after each code-writer or debugger unit, before commit. Not for full-PR review (use pr-reviewer) and not for deep React/TypeScript or accessibility review (use frontend-qa).
Implementation specialist for feature work, bug fixes, and planned changes. Receives tasks from planner or orchestrating session, writes production code following project conventions, mandatorily chains code-reviewer after each logical unit, writes tests inline, and dispatches the commit agent when all units are complete.
Git commit specialist. Use after completing a feature, fix, or meaningful change. Reads staged changes, writes a semantic commit message, and commits cleanly.
Root-cause debugging of concrete failures — a reproduced error, a stack trace, a failing test, or observably wrong runtime behavior. Use when investigation needs more than one inline tool call. NOT for code-quality concerns (use code-reviewer), writing tests for passing code (use test-writer), or review-only findings; debugger edits code and self-chains commit, so route only confirmed defects.
Full CAST agent registry — 23 agents with model assignments. Load when building an Agent Dispatch Manifest, orchestrating multi-agent workflows, or when you need to verify which model a specific agent runs on.
Assemble morning briefing sections into a structured markdown file. Use when writing the final briefing output after all data sources have been gathered.
Activate careful mode — require explicit confirmation before any Write, Edit, or Bash operations. Use when working on production code or sensitive systems.
Comprehensive CAST codebase audit — bugs, security, performance, test coverage. Dispatches 4 parallel researchers to scan the codebase and collates findings into a dated report. Runs monthly (first Monday, 08:00 local).
Shared CAST conventions for all agents. Loaded automatically via agent frontmatter.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
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.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
GITHUB_TOKENGitHub PAT for the github MCP server.
${user_config.GITHUB_TOKEN}Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Requires secrets
Needs API keys or credentials to function
Requires secrets
Needs API keys or credentials to function
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
CAST is a production-grade control plane for Claude Code built on three pillars: hook enforcement (every agent change is gated by validators —
cast-validate-all-hooks.shruns in CI and hookSpecificOutput shape is contract-validated), audit trail (cast.db with 36 tables records every session, agent run, routing decision, quality gate, and memory write), and a typed agent registry (23 agents, model-assigned across haiku 4.5 / sonnet / opus tiers, quality-gated, with frontmatter contracts). Define a workflow once; specialist agents plan, implement, review, test, and commit — automatically.
brew tap ek33450505/cast && brew install cast
git clone https://github.com/ek33450505/claude-agent-team.git
cd claude-agent-team
bash install.sh
CAST also ships as a Claude Code plugin. Two ways to load it:
From the marketplace (recommended):
/plugin marketplace add ek33450505/claude-agent-team
/plugin install cast
/plugin enable cast@cast
From a local checkout:
git clone https://github.com/ek33450505/claude-agent-team.git
claude --plugin-dir claude-agent-team/plugin
The plugin bundles CAST's curated agents, skills, commands, hooks, and the GitHub MCP server (provide a GitHub token via the plugin's GITHUB_TOKEN config to enable it; without a token the MCP server simply won't connect). It is opt-in (defaultEnabled: false) and complements install.sh rather than replacing it: install.sh remains authoritative for the runtime layer (~/.claude/scripts, cast.db, launchd jobs, git hooks). Until you run /plugin enable cast@cast, the SessionStart bootstrap does not run and hook symlinking + cast.db initialization will not occur. When both installs are present, the plugin's command hooks automatically defer to install.sh via a ~/.claude/config/cast-hook-owner sentinel that install.sh writes, so the two coexist safely without double-firing hooks.
Note: the
pushagent is not bundled (it depends on the install.sh-managed runtime). Plugin users push withbash ~/.claude/scripts/cast-push.sh <branch>(symlinked by the bootstrap) or via a fullinstall.sh. To include the opt-in extras tier (perf-sentinel, release-notes, api-contract, dep-auditor), regenerate locally:bash scripts/gen-plugin.sh --with-extras dist/cast-pluginthenclaude --plugin-dir dist/cast-plugin.
docs/tutorial/getting-started.md — install, verify, and run cast status in 5 minutes.
git commit and git push are hard-blocked by hooks. Code changes mandate a reviewer pass. You cannot skip this.code-writer implements; code-reviewer reviews; commit commits. They don't cross lanes.cast.db on your machine. No SaaS dashboard, no cloud lock-in.| Guide | Description |
|---|---|
| Tutorial | Install CAST and run your first agent dispatch |
| Compatibility Matrix | Claude Code version requirements and known breakages |
| Hook Authoring Guide | Write, test, and install custom hook scripts |
| Full Docs Index | All documentation with one-line descriptions |
What is CAST? · Architecture · Agents · Hooks · Observability · Ecosystem · Testing · Contributing · Stats
npx claudepluginhub ek33450505/claude-agent-team --plugin castComprehensive 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.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.