Skill Claude CodeCodex
Generate and review prevention rules auto-promoted from repeated failure patterns.
26 yesterday A 18 tokens
original MIT
Skill Claude CodeCodex
Govern Cursor SDK local, cloud, self-hosted, and subagent coding runs before they create branches or PRs.
26 yesterday A 30 tokens
original MIT
Skill Claude CodeCodex
Recall relevant past failures, prevention rules, and context packs before starting a coding task.
26 yesterday A 21 tokens
original MIT
Skill Claude CodeCodex
Search promoted lessons for corrective actions, lifecycle state, linked rules, and linked gates.
26 yesterday A 21 tokens
original MIT
Skill Claude CodeCodex
Status: shipped 2026-04-21. Test-backed. CLI-automatable. Safe to recommend publicly.
26 yesterday A 0 tokens
original MIT
Agent Memory
54Skill Claude CodeCodex
Give your agent persistent cross-session memory — recall what went wrong on similar tasks before starting, then capture whether the work succeeded or failed so repeated mistakes auto-promote into prevention rules. Runs locally via the ThumbGate MCP server (recall, capturefeedback, preventionrules, feedbackstats) — no…
26 yesterday A 162 tokens
original MIT
Skill Claude CodeCodex
Repeatable skill for deploying ApplyOps pages to GitHub Pages with full analytics.
26 yesterday A 0 tokens
original MIT
Skill Claude CodeCodex
Automated Bluesky reply monitoring and draft queueing for ThumbGate's acquisition engagement loop. Polls the AT Protocol notifications endpoint every 15 minutes, writes human-reviewable draft replies into a queue file, and never auto-posts without sign-off. Trigger when the user asks about Bluesky replies, engagement…
26 yesterday A 96 tokens
original MIT
Skill Claude CodeCodex
Repeatable skill for setting up Plausible, PostHog, and GA4 analytics keys in both local .env and Railway production environment variables.
26 yesterday A 0 tokens
original MIT
Skill Claude CodeCodex
HARD checklist before new skills, MCP tools, hooks/gates, plugins, or multi-agent workflows. Maps Hugging Face Context Course units 1–5 onto ThumbGate. Auto-invoke when creating SKILL.md, PreToolUse hooks, gate patterns, MCP tools, Grok workflows, slash commands, or when user says context engineering, HF context…
26 yesterday A 99 tokens
original MIT
Skill Claude CodeCodex
Orchestrate coding work with GSD (Capture→Clarify→Organize→Execute→Review) and Ralph Loop (Observe→Act→Feedback→Promote→Enforce). Use parallel agents/workflows for multi-faceted tasks. Auto-invoke when user says GSD, Ralph Loop, get shit done, work in parallel agents, context course, or all of it for context…
26 yesterday A 99 tokens
original MIT
Skill Claude CodeCodex
Repeatable skill for pulling checkout funnel analytics data from all sources into a readable local report.
26 yesterday A 0 tokens
original MIT
Skill Claude CodeCodex
Course-correct from over-planning to execution — when the agent has produced a plan, research, or options instead of doing work the user already approved, drop the analysis and execute the smallest end-to-end action now (branch, run, deploy, verify). Use when the user says "stop planning, just do it", "why are you…
26 yesterday A 159 tokens
original MIT
Skill Claude CodeCodex
Show ThumbGate's enforcement record — how many risky actions were actually blocked versus warned, which gates fire most, the tokens/damage saved, and the full feedback to check to rejection pipeline. Reads live enforcement counters via the gatestats and enforcementmatrix MCP tools (CLI fallback npx thumbgate…
26 yesterday A 162 tokens
original MIT
Skill Claude CodeCodex
Skill "thumbgate-brand-voice" from IgorGanapolsky/ThumbGate, covering thumbgate brand voice, when to use, how to use (in order) and the one rule that overrides everything.
26 yesterday A 160 tokens
original MIT
Skill Claude CodeCodex
Health-check whether ThumbGate is actually wired into this agent — PreToolUse/SessionStart hooks installed, MCP server reachable, lesson store present, statusline, and overall agent-readiness — then report exactly what to fix. Runs the existing npx thumbgate doctor audit and the checkoperationalintegrity MCP tool. Use…
26 yesterday A 168 tokens
original MIT
thumbgate
65MCP server Claude CodeCodexCursor +2
Pre-action gates that block AI agents from repeating known mistakes. Runs locally from the thumbgate npm package.
26 yesterday A
tokens not measured
original MIT