ecc
179.0k·2.3K·
Battle-tested Claude Code plugin for engineering teams — 50 agents, 188 skills, 68 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
today
affaan-mSet up autonomous iterative code optimization loops using Claude CLI, with git checkpoints, tiered quality gates, secondary metrics, and structured output. Auto-scout codebases to detect project types, build systems, tests, and metrics; persist feedback on loop designs across sessions for continuous refinement.
npx claudepluginhub joshuaoliphant/claude-plugins --plugin autoloopMUST use when the user wants autonomous, iterative optimization — letting Claude run experiments unattended. Trigger: "autoloop", "autoresearch", "experiment loop", "hill-climbing", "optimize overnight", "karpathy loop", "let Claude optimize while I sleep", "automate trying different approaches", "set up a loop to improve this", "run experiments overnight", or any request for iterative improvement with a scalar metric. Generates program.md + immutable runner script (auto/run.sh) with tiered quality gates and structured METRIC output, ready to run with claude --dangerously-skip-permissions.
Save autoloop experiment feedback proactively. MUST trigger when the user corrects loop design ("don't use that metric", "always include this gate", "wrong quality gate") or confirms good output. Also trigger on explicit requests: "save this feedback", "show my feedback", "clear feedback", "loop preferences", "autoloop settings", "consolidate feedback", "bake in my preferences". Feedback loaded automatically when designing new experiment loops.
A collection of Claude Code plugins for productivity and learning workflows.
# Add this marketplace
/plugin marketplace add joshuaoliphant/claude-plugins
# Install any plugin
/plugin install <plugin-name>@oliphant-plugins
Create evidence-based spaced repetition flashcards using cognitive science principles from Andy Matuschak's research. Applies the 5 properties of effective prompts (focused, precise, consistent, tractable, effortful) to ensure cards actually work for long-term retention.
Features: Quality validation, knowledge-type workflows (factual, conceptual, procedural, salience), anti-pattern detection, template support, deck management, batch operations.
Requirements: Mochi.cards account + MOCHI_API_KEY environment variable.
/plugin install mochi-creator@oliphant-plugins
export MOCHI_API_KEY="your_api_key_here"
Adaptive autonomous SDLC with 5 skills covering the full development lifecycle:
bd commands) with explicit dependencies/plugin install autonomous-sdlc@oliphant-plugins
Build web applications where an AI agent dynamically generates HTML UI using hexagonal/ports-and-adapters architecture with HTMX for interactivity and MCP tools for data operations.
Stack: Claude Agent SDK + FastAPI + HTMX + Tailwind CSS.
/plugin install hexagonal-agents@oliphant-plugins
export ANTHROPIC_API_KEY="your_key_here"
Capture solved problems and retrieve past solutions as structured YAML-frontmatter files for grep-based retrieval across sessions and projects.
/plugin install compound-knowledge@oliphant-plugins
Generate autonomous experiment loops that iteratively improve code by editing, running, measuring a scalar metric, and keeping improvements via git commit/reset. Based on Karpathy's autoresearch pattern.
Generates: program.md + auto/run.sh with tiered quality gates, ready to run with claude --dangerously-skip-permissions.
/plugin install autoloop@oliphant-plugins
Contributions are welcome! Feel free to submit issues or pull requests.
MIT
Autonomous experiment loop for optimizing any measurable target
Autonomous experimentation skill — your AI coding agent designs experiments, tests hypotheses, discards failures, keeps wins. Runs overnight while you sleep.
Use when debugging, investigating root causes, designing experiments, or performing scientific analysis — enforces hypothesis-driven reasoning, evidence-first observation, causality validation, and structured output templates. Use when facing unknowns, repeated failures, or complex investigations requiring rigorous methodology.
Autonomous experiment loop for any project type. Inspired by karpathy/autoresearch.
AI development loop — orchestrator distributes tasks to headless workers, independent auditor verifies, structural enforcement auto-blocks downstream on upstream failure. Full-cycle validated with 10-scenario test harness.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Battle-tested Claude Code plugin for engineering teams — 50 agents, 188 skills, 68 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
affaan-mOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim