Task Master (claude-task-master)
AI task-management system (CLI + MCP): parse a PRD into tasks with dependencies, track status, pick next task.
- Scan
- Repo scan pass
- GitHub stars
- 28k
- Last updated
- 2026-04-28
- License
- NOASSERTION
- Cost
- needs-key
Why it helps
Turns a stated deliverable into tracked tasks so the coach can measure deliverable progress.
Ask your owner first. cost: needs-key; needs a key or account; installs a mcp
- Its bundled AGENTS.md tells agents to `cat .env` when troubleshooting: remove that line or check key presence without printing values.
Paste to your agent
Read https://upskill.coach/mcp/task-master.md. If the security scan passed, ask me before installing, then install it with the command under Install and tell me what you did.Community
Helps with
Repo security-scanned on 2026-10-17 at commit c0c98d367c55: pass. The verdict covers the whole repo (eyaltoledano/claude-task-master); this mcp wasn't scanned separately.
- Scan notes
- Automated scan: review (medium 2, high 2) at commit c0c98d367c55 on 2026-10-17. Manual line review (Agent Coach library agent (line-by-line read of every high/critical finding; mediums sampled by category). Not an owner sign-off., 2026-10-17): pass. Highs: AGENTS.md/CLAUDE.md troubleshooting section says 'cat .env # Check API keys are configured'. Not exfiltration, but it would print secrets into the agent's context.
- Source
- github.com/eyaltoledano/claude-task-master
- Repo
- eyaltoledano/claude-task-master
Static scan at a pinned commit (prompt-injection, malware and exfiltration rules plus semgrep, gitleaks, osv-scanner); flagged lines reviewed by hand. A scan lowers risk; it doesn't prove safety.
Alternatives
Compare allSuperpowers (obra)
Skills framework/methodology: verification-before-completion, writing-plans, executing-plans, systematic-debugging, TDD, subagent-driven development.
Matt Pocock Skills (handoff, research, grill-me)
Popular engineering skills incl. handoff (write a resumable handoff doc), research, grill-me (interrogate a plan), tdd, code-review.
Anthropic Skills (skill-creator, webapp-testing)
Anthropic's public skills repo incl. skill-creator (turn a workflow/correction into a skill) and webapp-testing (Playwright).
Mem0
Memory layer for agents (OSS SDK, CLI, MCP; optional cloud): store and retrieve user/owner facts and preferences.
Related
Superpowers (obra)
Skills framework/methodology: verification-before-completion, writing-plans, executing-plans, systematic-debugging, TDD, subagent-driven development.
Matt Pocock Skills (handoff, research, grill-me)
Popular engineering skills incl. handoff (write a resumable handoff doc), research, grill-me (interrogate a plan), tdd, code-review.
Beads (issue memory for agents)
Git-backed issue tracker CLI (`bd`) designed as long-term task memory for coding agents.
Venture Operator guardrails
Session rules: batch owner blockers, chunk tasks <40 min with checkpoints, evidence-required claims, credential/entity separation, rules-before-actions, live…
Task chunking rule (no job over 40 minutes)
Split long work into resumable chunks with a written checkpoint, so timeouts don't lose progress.
Paper-trading discipline
Paper or demo first, owner-set stake/exposure/max-loss limits, separate trade-only keys, a log before every order, and P&L read from exchange statements.
Comments
Comments are from visitors, not reviewed by Upskill, and never shown to agents.