mtk

Plugin mtk from marketplace moberghr in moberghr/mtk-agent-toolkit. Commands read from the repo's manifest — today.

Skills (33)

• batch-fix

  Use to apply review findings or several small independent corrections across more than 3 files in one batch, with no new contract or architecture — broader than fix, lighter than implement.

• brainstorming

  Use before spec writing when the approach is unclear, several designs or ways to build it are plausible, or the engineer wants to explore alternatives before committing.

• code-review-and-quality

  Review a PR (pull request), branch or diff outside implement — runs the compliance, silent-failure, test and architecture lanes with full lane accounting.

• code-simplification

  Use after a feature or fix is verified to simplify the changed code without changing behavior — wraps Claude Code's /simplify with finance and security carve-outs.

• context-engineering

  Use when starting a session, switching between planning/implementation/review phases, entering unfamiliar code, or when output drifts from project norms.

• fix

  Use for a bug, failing test, error or small config change whose fix stays within 1-3 files and needs no formal spec — escalates to implement if the scope grows.

• handoff

  Use when handing in-progress work to a teammate or ending a session with unfinished, uncommitted work — writes a short recovery note with branch, state, decisions and resume steps.

• implement

  Use for substantial work that adds a feature, a public contract such as an endpoint, or a multi-file behavior change; the full loop of spec, plan, batched implementation, verification and review.

• incremental-implementation

  Use when executing an approved multi-file implementation to ensure each batch compiles, tests, and stays within the approved manifest.

• instructions

  Audit AGENTS.md/CLAUDE.md for rot with verify-references/verify-commands, or capture a session's discovered commands and gotchas — append-only diffs, applied only with approval.

• lessons

  Team lessons lifecycle — capture a correction or golden path, mine past transcripts, refresh stale anchors, promote native memory to tasks/lessons.md; reject-by-default, writes need approval.

• mtk-doctor

  MTK install health check — core files, hooks, integrity, active config and environment, with JSON output, safe auto-repair and raw usage counts; use when MTK seems broken or misconfigured.

• mtk-setup

  One-stop setup entry point that bootstraps a repo or re-runs architecture audit

• mtk

  Unified entry point that routes natural language requests to the right MTK skill

• planning-and-task-breakdown

  Use after a spec is approved and before multi-file implementation begins, to break work into verifiable batches with checkpoints.

• pre-commit-review

  Fast security-focused review of staged changes before every commit, checking only critical compliance rules

• prior-work-check

  Use before approving a spec or starting a multi-file implementation to confirm no existing skill, helper, or handler already covers the proposed work.

• promote-lesson

  Deprecated alias for `lessons promote` (kept for one release) — promotes a native-memory rule to the team-wide tasks/lessons.md.

• repo-health

  Periodic AI-readiness report — 9-asset action checklist, audit drift, and suggest-only reviewer-feedback phrases mined from the last N merged PRs.

• research-context

  Use when a decision needs current external info, not local sources — latest-version behavior, recommended practices, upgrade or migration guides; researches the web and returns a cited brief.

• security-and-hardening

  Use when the change touches auth, secrets, audited state, audit trails, infrastructure, or external inputs — treat security as a design constraint, not final polish.

• setup-audit

  Audit the repo to extract architecture principles, or with --merge unify audits from multiple repos into a single team-wide document

• setup-bootstrap

  One-time repo setup that detects tech stack, audits the codebase, pulls coding guidelines, and generates a project-specific AGENTS.md plus a CLAUDE.md shim

• setup-refresh

  Refresh generated setup artifacts (principles, conventions, detected tools, AGENTS.md, configs, indexes) against codebase drift — proposes diffs for engineer-edited files instead of overwriting.

• spec-drift-detection

  Use after implementation completes and before review begins, to verify the actual change matches the approved spec — files touched, public contracts added, security impact, and declared scope.

• spec-driven-development

  Use when the task is a new feature, breaking change or multi-file change whose spec and design should be approved before any code is written.

• subagent-implementation

  Use instead of incremental-implementation for 3+ batches, 6+ non-mechanical files, or non-none security_impact — one fresh implementer subagent per batch with orchestrator drift checks.

• tech-stack-dotnet

  .NET stack context for workflow skills — dotnet build, test and migration commands, EF Core and MediatR patterns, analyzer setup, C# coding guidelines and reference file paths.

• tech-stack-python

  Python stack context for workflow skills — pytest, mypy and ruff commands, SQLAlchemy and Alembic guidance, FastAPI, Django and Flask patterns, and reference file paths.

• tech-stack-typescript

  TypeScript/JavaScript stack context — package manager build and test commands (Vitest, Jest), Prisma and Drizzle guidance, React, React Native/Expo, Next.js, Tauri and Node patterns.

• verification-before-completion

  Use before reporting any task, batch or fix as complete — requires fresh evidence from tests or commands actually run for every completion claim.

• workflow-artifacts

  Use to create, update, and read durable workflow state under .mtk/workflows/ so orchestration survives compaction, crash, and session handoff.

• writing-skills

  Use when creating a new skill for this toolkit — ensures the skill follows the anatomy, CSO principle, and is tested against agent rationalizations before shipping.

Hooks (16)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/session-start"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/security-gate.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/format-on-edit.sh" --flush-before-verify

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/push-gate.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/scope-guard.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/config-guard.sh"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/evidence-ledger.sh"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/context-guard.sh"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/spec-approval-trigger.sh"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/format-on-edit.sh"

• Stop

  "${CLAUDE_PLUGIN_ROOT}/hooks/verify-completion"

• Stop

  "${CLAUDE_PLUGIN_ROOT}/hooks/format-on-edit.sh" --flush

• Stop

  "${CLAUDE_PLUGIN_ROOT}/hooks/workflow-continuation.sh"

• Stop

  "${CLAUDE_PLUGIN_ROOT}/hooks/cost-tracker.sh"

• SubagentStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-context.sh"

• PostCompact

  "${CLAUDE_PLUGIN_ROOT}/hooks/compact-archive.sh"

Similar plugins