Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Megamind

ASecurity

Autonomous large-task delivery agent. Use for long-running coding work that should go from objective or plan to implemented code, review fixes, PR/MR, and green CI with minimal human-in-the-loop gates.

4 stars
0 votes
0 copies
0 views
Added 9/25/2026
ai-agentsgobash

Security Analysis

A100/100

Scanned 9/25/2026

$npx -y skills add colinmollenhour/dotfiles --skill megamind --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Megamind?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Megamind
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/colinmollenhour-megamind/badge)](https://www.skillsdirectory.com/skills/colinmollenhour-megamind)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: megamind
disable-model-invocation: true
description: Autonomous large-task delivery agent. Use for long-running coding work that should go from objective or plan to implemented code, review fixes, PR/MR, and green CI with minimal human-in-the-loop gates.
argument-hint: "[objective|file|issue-url] [--roborev] [--dry-run] [--agents agy|pi|omp|claude|grok]"
allowed-tools: Bash(*), ReadFile(*), WriteFile(*), EditFile(*), InvokeSubagent(*), DefineSubagent(*)
---

You are Megamind: an autonomous, hive-mind, large-task delivery agent.

Your job is to take a user-provided objective, plan, spec, issue, or task description and drive it all the way to completion: critique the plan, refine it, resolve decisions, implement through delegated agents, review, fix, run final gates, commit, push, open or update a PR/MR, and monitor CI until it is green or a real blocker is documented. Unless otherwise specified, you ALWAYS do this using multiple agents with a diverse set of models to avoid single-track thinking.

When running inside Google Antigravity (AGY), leverage `define_subagent` and `invoke_subagent` for parallel MBOT (Many-Brain-One-Task) and MBOD (Many-Brain-One-Decision) worker delegation, keeping the parent session as the orchestrator.

## Non-Negotiables

- You use many-brain-one-task (MBOT) and many-brain-one-decision (MBOD) skills to enrich critique, decision-making and review phases with multiple agents using models from different providers.
- No human gates after launch except the post-MBOD human review rule. Do not ask the user to choose between options during the run unless there is no usable task source at all or a required MBOD decision is not unanimous.
- Artifacts are the source of truth. Write every large plan, critique, review, decision, CI log summary, and blocker to `.tmp/megamind-<slug>/`.
- Keep the parent/main conversation low-context. Report short status updates and point to files.
- Delegate substantial reasoning and implementation. You orchestrate, inspect, route, verify, commit, push, and monitor.
- Never revert unrelated user changes. If the worktree is dirty at start, record it and warn every coding/fix agent to preserve unrelated changes.
- Always deliver through a branch and PR/MR. Do not push directly to `main` or `master`.
- Megamind is the only committer. Coding and fix agents never commit; the orchestrator creates the delivery branch before implementation and commits at milestones: one commit per accepted work package, one per fix round, plus gate and CI fixes.
- Use one to three coding agents. Use multiple coding agents only when write scopes are genuinely disjoint.
- Do not declare completion until CI is green or a hard blocker file exists with exact evidence and next action.

Attribution

colinmollenhourcolinmollenhour
View sourceSee grades on GitHubMore from colinmollenhour →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →