By Jagoda11
The Jagoda Toolkit made by Jagoda Cubrilo Claude Code skills, hooks, and agents for TS monorepo dev. Requires CodeGraph (npm i -g @colbymchenry/codegraph) and jq (brew/apt/dnf install jq).
Write tests for code changes while preserving harmonic constraints, matching local test patterns, and verifying with format/lint/typecheck/test. <example> Context: User wants tests for code they just wrote. user: "Write tests for the classifier service" assistant: "I'll use the test-writer agent to create tests for the classifier service." <commentary> User explicitly asking for tests for a specific file. </commentary> </example> <example> Context: New module was added and needs test coverage. user: "Add tests for the user schemas" assistant: "I'll use the test-writer agent to write tests matching existing patterns." <commentary> Test coverage needed for a new module. Trigger test-writer. </commentary> </example>
Checks $PAGE UI in Chrome via DevTools MCP. Reports errors — never fixes anything. <example> Context: User wants to check the page UI works in Chrome. user: "Check the UI for the dashboard" assistant: "I'll use the ui-verifier agent to navigate to the page, test submissions with real data, and report any issues." <commentary> UI-only verification. User wants Chrome check, not CI or DB. </commentary> </example> <example> Context: User checked the CI, now wants UI verification. user: "CI passed, now check the UI for the settings page" assistant: "I'll use the ui-verifier agent to verify the settings page in Chrome." <commentary> User is running agents individually in sequence. UI check after CI pass. </commentary> </example>
Deep architecture audit for any feature or change. Runs failure mode analysis, boundary audit, test gap mapping, contract compliance, data flow tracing, and risk prioritization. Use for major features, critical refactors, or when things feel architecturally wrong.
Structured task handoff. Use when user wants to plan or set up a task before executing — asks 5 intake questions (mode, goal, context, format, unknown_ok) and confirms in one sentence before starting.
Launch a named expert protocol. Usage: /protocol <name> <task>. Run /protocol with no args to list available protocols.
AI-agent compatibility audit. Use when evaluating whether code changes are safely readable, analyzable, and modifiable by AI agents. Checks determinism, explicitness, complexity, and boundary clarity.
Production-readiness audit for authentication. Use when auth code changes or when auth feels fragile, unclear, or unsafe. Covers OIDC, sessions, tokens, route protection, and secret management.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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.
Uses power tools
Uses power tools
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
A Claude Code plugin — skills, hooks, and agents for TypeScript monorepo development.
New to Claude Code? Feeling lost? Install this toolkit and you've got a working baseline — pre-flight checks, review skills, safety hooks, and agents — without having to wire it all up yourself.
jc is a single Claude Code plugin bundling skills, commands, hooks, and agents for TypeScript monorepo development. It gives Claude:
rtk for token savingsjq is required by the security hooks (block-git-commit-protected, no-overwrite, scan-credentials, verify-on-write).
# macOS
brew install jq
# Debian / Ubuntu
sudo apt install jq
# Fedora / RHEL
sudo dnf install jq
claude plugin marketplace add Jagoda11/the-jagoda-toolkit
claude plugin install jc@the-jagoda-toolkit
| Skill | Purpose |
|---|---|
/jc:start | Pre-flight: load CodeGraph, check branch and recent changes, pre-load core tools |
/jc:start-ui | Same as /jc:start plus verify Chrome DevTools and navigate to the frontend |
/jc:prompt | Structured task handoff — asks 5 intake questions before executing |
/jc:audit | Deep architecture audit: failure modes, boundary audit, test gaps, data flow, risk prioritization |
/jc:protocol | Router for named expert panels — /jc:protocol <name> <task> |
/jc:protocol-brains | 11-expert backend/architecture panel (DB, TS, migration, monorepo, multiagent, orchestration) |
/jc:protocol-pinky | 16-expert frontend panel with dynamic UI-lib routing |
/jc:review | Smart router — detects branch changes and recommends which audit to run |
/jc:review-pr | Full pre-merge gate — automated checks, governance, AI patch safety score |
/jc:review-auth | Auth production-readiness audit (OIDC, sessions, tokens, route protection, secrets) |
/jc:review-ai-compat | AI-agent compatibility — determinism, explicitness, complexity, boundary clarity |
/jc:review-cicd | CI/CD reliability — pipelines, Dockerfiles, K8s, Skaffold, GitHub Actions |
/jc:review-design | 24 structural design principles for agent-readable code |
/jc:review-monorepo | Workspace boundaries, dependency direction, domain ownership, shared-package bloat |
/jc:review-test-strategy | Test architecture, coverage, flakiness — produces scored JSON contract |
| Command | Purpose |
|---|---|
/jc:verify | Run lint, typecheck, and test on affected workspaces (auto-detects package manager) |
/jc:techdebt | Review changed files for tech debt lint can't catch — duplication, dead code, naming drift |
| Agent | Purpose |
|---|---|
jc:test-writer | Writes tests for code changes, preserves harmonic constraints, verifies with format/lint/typecheck/test |
jc:ui-verifier | Verifies a page UI end-to-end in Chrome via DevTools MCP; reports only, never fixes |
| Hook | When | What | Modifies | Can Block | Failure Behavior |
|---|---|---|---|---|---|
| rtk-rewrite.sh | PreToolUse (Bash) | Rewrites shell commands through rtk for token savings | command only | no | falls back to original command |
| block-git-commit-protected.sh | PreToolUse (git commit) | Blocks commits on protected branches | no | yes | blocks commit |
| no-overwrite.sh | PreToolUse (Write) | Prevents accidental file overwrites | no | yes | blocks write |
| scan-credentials.sh | PostToolUse (Edit / Write / MultiEdit) | Scans newly written content for credentials | no | yes | flags and blocks if configured |
| verify-on-write.sh | PostToolUse (Edit / Write / MultiEdit) | Auto-runs verification after file writes | no | no | reports failures |
| sync-skills.sh | SessionStart | Syncs local skills | no | no | logs failure |
All hooks operate locally on Claude Code tool payloads and repository context.
npx claudepluginhub jagoda11/the-jagoda-toolkit --plugin jcFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
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.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
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.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Complete developer toolkit for Claude Code