Enable AI agents to iteratively self-direct in pursuit of open-ended goals with state continuity across conversations through iteration journals
Analyze another branch to extract findings, decisions, and insights
Detailed status report for single autonomy branch
Save current iteration progress before conversation compaction or as interim checkpoint
Compare two autonomy branches to show different approaches and outcomes
Create a new open-ended goal for autonomy tracking
Use when analyzing autonomy branches via git log, generating Python scripts for computational analysis of iteration data, and producing formatted reports for list-branches, branch-status, or compare-branches operations
Use when starting an iteration to read and structure recent journal entries (last 3-5 iterations) for context loading
Use when starting an iteration with >5 previous iterations to condense older journal entries into a summary document
Use when user wants detailed status report for single autonomy branch including iteration timeline and metrics progression
Use when analyzing another branch's iteration journals to extract findings, decisions, and insights from divergent work
Use when saving current iteration progress mid-conversation, before context compaction, or at interim pause points
Use when user wants to compare two autonomy branches to see different approaches, metrics, and outcomes
Use when setting up a new open-ended goal for autonomy tracking, before starting the first iteration
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Institutional knowledge marketplace for AI agent teams, maintained by Tilmon Engineering.
This marketplace hosts a collection of Claude Code plugins that capture institutional knowledge and enable AI agents to perform specialized tasks with rigorous, repeatable methodologies.
Structured research methods for AI agents conducting rigorous, reproducible data analysis and qualitative research.
Version: 1.0.0
Key capabilities:
Enable AI agents to iteratively self-direct in pursuit of open-ended goals with state continuity across conversations through iteration journals.
Version: 1.0.0
Key capabilities:
Install from GitHub:
claude plugin install tilmon-engineering/claude-skills
Strongly recommended dependency: ed3d-plugins provides plan-and-execute workflows, brainstorming, TDD, and other development skills that complement these plugins.
claude plugin install ed3dai/ed3d-plugins
To add a new plugin to this marketplace:
plugins/[plugin-name]/.claude-plugin/plugin.json with metadataskills/ and/or agents in agents//.claude-plugin/marketplace.json to include new pluginclaude plugin validate .plugins/[plugin-name]/
├── .claude-plugin/
│ └── plugin.json # Plugin metadata
├── skills/ # Optional: Claude Code skills
├── agents/ # Optional: Specialized agents
├── templates/ # Optional: Template files
└── README.md # Plugin documentation
MIT - See LICENSE for details.
npx claudepluginhub tilmon-engineering/claude-skills --plugin autonomyStructured research methods for AI agents - hypothesis testing, exploratory analysis, comparative analysis, and qualitative research
Proactive enhancement layer for AI agents — learns user patterns from any memory store, upgrades prompts into full intent, takes engineer-grade initiative that advances the goal instead of generic filler, predicts the next request, verifies everything before delivery, scans for AI slop, orchestrates subagents when available, onboards itself to any host on first run, and runs a self-improvement loop that sharpens its own heuristics. Universal adapter runs on Claude Code, Codex, Hermes, OpenClaw, opencode, Cursor, Gemini CLI, and custom loops.
Core agents for general-purpose tasks. Other plugins expect this to exist.
Automatically detects and loads AGENTS.md files to provide agent-specific instructions alongside CLAUDE.md. Enables specialized agent behaviors without manual intervention.
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.