Autonomously made by autonomous agents. Multi-agent orchestra, S&QA gating, 6 testing agents, 16 battle-tested skills, self-improvement loops. Built in production, not theory.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Audit the MCP server experience from an agent's perspective. Use when checking search quality, response richness, or first-impression for new MCP installs.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Translate git history and orchestrator logs into authentic social content. Use when turning recent technical work into tweets, Dev.to posts, or changelog entries without manual summarisation.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex needs its repo
Red team the staging environment with injection attacks, rate limit probes, and auth bypass attempts. Use before major releases or when adding new user-input surfaces.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Deploy Your Project to production safely. Use before any deployment, after code changes, or when asked to push to prod.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Strategy for getting Your Project's first paying customer. Use when discussing revenue, pricing, monetization, or what to sell. Based on Minimalist Entrepreneur principles adapted for our stage.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
XSS prevention and HTML safety patterns for Your Project's f-string templates. Use when writing or reviewing any route file that renders HTML.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Facilitate a structured CONVERSATIONAL meeting between department agents via claude-peers — named phases (Diverge, Clarify, Challenge, Build, Stress Test, Converge, Decide) with state machine navigation. Agents push back on each other and build on each other's ideas. Minimum path: Diverge → Challenge → Build → Stress…
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Manage the 6-department orchestra via claude-peers. Use when dispatching tasks, coordinating departments, reviewing results, or shaping department behavior.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Run a maker outreach campaign through the orchestra. Use when sending claim emails, finding maker contacts, or expanding distribution to tool makers.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Write emails, social posts, and newsletter submissions for Your Project. Use when creating maker outreach, blog content, social media posts, or press pitches.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Safely update data on the production Your Project database via Fly SSH. Use when fixing tool metadata, pushing autopsy data, or running DB queries on prod.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex needs its repo
Research & Development Architect — researches improvements, writes proposals, manages autoresearch loops. Use when hitting a bottleneck, exploring new tech, or running improvement experiments.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Structured S&QA review framework for every task. Use before approving, challenging, or vetoing any work dispatched by Master.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Navigate the staging site as a specific developer persona and report UX confusion points. Use when auditing flows for a specific user type before a release.
Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Audit LLM token usage across departments, identify waste, and recommend model/caching optimisations. Use when costs are rising or before scaling the orchestra.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: