The Jagoda Toolkit

Plugin jc from marketplace the-jagoda-toolkit in Jagoda11/the-jagoda-toolkit. Commands read from the repo's manifest — today.

Skills (15)

• audit

  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.

• prompt

  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.

• protocol

  Launch a named expert protocol. Usage: /protocol [name] [task]. Run /protocol with no args to list available protocols.

• protocol-brains

  Protocol Brains — 11-expert backend/architecture panel. 2 Database, 2 TypeScript architects, 1 Legacy Migration, 1 React, 1 Test, 1 Monorepo, 2 Multiagent workflow, 1 Orchestration.

• protocol-pinky

  Protocol Pinky — 16-expert frontend panel with dynamic UI-lib routing. 2 React architects, 1 TS architect, 1 State/Data, 1 MUI, 1 UX/a11y, 1 Contracts, 1 Test, 1 i18n, 1 Security, 1 Performance, 1 Business Impact, 1 Backend Contract, 1 Monorepo, 1 Tailwind, 1 UI Component Library.

• review-ai-compat

  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.

• review-auth

  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.

• review-cicd

  CI/CD and deployment reliability audit. Use when pipeline configs, Dockerfiles, K8s manifests, Skaffold config, or GitHub Actions workflows change. Checks build integrity, environment parity, secret hygiene, and rollback safety.

• review-design

  Design principles audit. Use when evaluating whether code changes follow the 24 structural design principles for agent-readable code. Checks file design, separation of concerns, schema integrity, agent reliability, and safety.

• review-monorepo

  Monorepo boundary audit. Use when shared packages change, new workspaces are added, or import patterns feel tangled. Checks workspace boundaries, dependency direction, domain ownership, and shared package bloat.

• review-pr

  Full PR review as a merge gate. Use before merging any non-trivial PR. Checks automated validation, governance principles, anti-entropy rules, harmonic constraints, code conventions, and production readiness.

• review-test-strategy

  Systemic review of test strategy and coverage. Use when tests feel weak, flaky, slow, or unclear — or when test-related code has changed. Triggers on "test strategy", "test coverage", "are the tests good enough", "flaky tests", or "review the tests".

• review

  Smart router that detects branch changes and recommends which audit skill(s) to run. Use this when starting a review or when unsure which audit to run.

• start-ui

  Pre-flight with Chrome. Runs /start then confirms Chrome DevTools tools are available for UI testing. Use instead of /start when you need browser access.

• start

  Pre-flight for a coding session. Loads CodeGraph, checks branch and recent changes, pre-loads core tools, and establishes session workflow rules. Use at start of a coding session, when the user asks to "start", or before any non-trivial task.

Slash commands (2)

• /jc:techdebt

  Review changed files for tech debt lint can't catch

• /jc:verify

  Run lint, typecheck, test on affected workspaces only. Auto-detects package manager. Use after code edits when the user asks to verify, lint, typecheck, or test affected workspaces.

Subagents (2)

• test-writer

  Write tests for code changes while preserving harmonic constraints, matching local test patterns, and verifying with format/lint/typecheck/test.\n\n[example]\nContext: User wants tests for code they just wrote.\nuser: \"Write tests for the classifier service\"\nassistant: \"I'll use the test-writer

• ui-verifier

  Checks $PAGE UI in Chrome via DevTools MCP. Reports errors — never fixes anything.\n\n[example]\nContext: User wants to check the page UI works in Chrome.\nuser: \"Check the UI for the dashboard\"\nassistant: \"I'll use the ui-verifier agent to navigate to the page, test submissions with real data,

Hooks (9)

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/content-safety-context.py"

• UserPromptSubmit

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/content-safety-context.py"

• PreToolUse

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/confirm-codex-config.py"

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/rtk-rewrite.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/block-git-commit-protected.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/no-overwrite.sh

• PostToolUse

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/escape-unicode-tags.py"

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/scan-credentials.sh

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/verify-on-write.sh

Similar plugins