Task Master (Grade A)Security-tested development skill for Claude AI. Grade A. Break a high-level request into ordered, actionable tasks. Use when the user asks to break down into tasks, create a plan, or list steps.

Why You Should Use This?

Individual: 30%+ token savings, stop repeating standards, security guardrails, instant scaffolding. Teams: Consistent AI behavior, day-one onboarding, codified patterns, compounding cost savings. Organizations: Always-on compliance, same standards across 1,000 projects, central governance, measurable ROI.

Asked by Ximenez Alvarado · Mar 14, 2026

What You Can Customize?

Project: Name, description, repo URL. Tech Stack: Language, framework, tools (e.g., TypeScript + Express or Python + FastAPI). Paths: Directory structure for handlers, services, and common code. Domain: Business entities like Order, Product, Customer with lifecycle states. Patterns: Code patterns such as a 7-step handler flow or error handling strategy. Testing: Quality gates like 90% coverage, test/lint/type-check commands. Database: Conventions like soft delete field, timestamp columns, naming. Packages: Internal packages settings (e.g., @your-org scope, registry URL). Conventions: Git and workflow rules like branch prefixes, commit format, PR templates.

Asked by Tunde Balogun · Mar 10, 2026

What it detects?

Language: Detects tsconfig.json, go.mod, Cargo.toml, requirements.txt, pom.xml, file extensions. Framework: Detects dependencies in package.json or requirements.txt (React, Express, Django, Spring, etc.). Database: Detects ORM configs (prisma/, sequelize, typeorm), .sql files, migration folders. Testing: Detects jest.config., vitest, pytest, cypress/, playwright.config. Infrastructure: Detects Dockerfile, terraform/, cdk.json, serverless.yml, cloud SDK dependencies. CI/CD: Detects .github/workflows/, .gitlab-ci.yml, Jenkinsfile.

Asked by Yelena Popova · Jan 18, 2026

What's Inside?

Rules (47): Enforce coding standards on every AI interaction, always on. Agents (62): Specialized assistants for complex tasks, on demand via /agent-name. Skills (50): Step-by-step guided workflows with checklists, triggered contextually. Commands (37): Lightweight, token-efficient quick actions, on demand via /command. Hooks (12): Automation scripts in the AI loop, event-driven before/after actions. Templates (9): Scaffolding for handlers, components, tests, etc., referenced by skills and agents.

Asked by Mireille Dupont · Jan 3, 2026

How It Works?

Layer 1 — Pre-Processing: Hooks inject project context and block dangerous commands before your prompt reaches the AI. Layer 2 — Rules Engine: 47 always-on rules enforce token efficiency, security, architecture, code standards, database conventions, and testing thresholds. Layer 3 — Specialized Processing: The right component activates — an agent, skill, or command — based on your prompt. Layer 4 — Post-Processing: Hooks validate output, auto-format, scan for secrets, and verify coverage.

Asked by Ulrik Madsen · Dec 31, 2025