From thumbgate
Captures thumbs-up/down feedback on AI agent actions, auto-converts repeated failures into prevention rules, and blocks known-bad tool calls via MCP PreToolUse hooks. Useful for safety guardrails with any MCP-compatible agent.
How this skill is triggered — by the user, by Claude, or both
Slash command
/thumbgate:thumbgateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Pre-action gates that stop AI coding agents from repeating known mistakes.
Pre-action gates that stop AI coding agents from repeating known mistakes.
npx thumbgate init
This installs the MCP server and wires it into your agent's tool configuration. No API keys required for the free tier.
Or install globally:
npm install -g thumbgate
thumbgate init
Add to your agent's MCP config (e.g., claude_desktop_config.json or .cursor/mcp.json):
{
"mcpServers": {
"thumbgate": {
"command": "npx",
"args": ["-y", "thumbgate"]
}
}
}
When an agent action succeeds or fails, capture structured feedback:
After a failure pattern repeats (default: 2 occurrences), ThumbGate auto-generates a prevention rule. These rules are injected into agent context before every tool call, blocking the known-bad pattern before it executes.
Gates intercept tool calls via the MCP PreToolUse hook. Each gate checks the proposed action against:
If a match is found, the gate blocks execution and surfaces the prior failure context.
Bounded retrieval of relevant feedback history for the current task. The agent gets exactly the lessons that matter, not the entire history.
| Tool | Description |
|---|---|
capture_feedback | Record thumbs-up/down with structured context |
search_lessons | Query the lesson DB by keyword or semantic similarity |
get_prevention_rules | Retrieve active prevention rules for the current context |
session_primer | Get session handoff context (last task, next step, blockers) |
export_dpo | Export feedback pairs in DPO training format |
| Free | Pro | Team | |
|---|---|---|---|
| Feedback capture | 3/day | Unlimited | Unlimited |
| Lesson search | 5/day | Unlimited | Unlimited |
| Active gates | 5 | Unlimited | Unlimited |
| Dashboard | - | Yes | Yes |
| DPO export | - | Yes | Yes |
| Seats | 1 | 1 | Per-seat |
| Price | $0 | $19/mo | $49/seat/mo |
Start a 7-day free trial of Pro: https://thumbgate-production.up.railway.app/go/pro?utm_source=skill
ThumbGate works with any MCP-compatible agent:
npx claudepluginhub igorganapolsky/thumbgateGives Claude persistent cross-session memory: recall past failures before starting tasks, capture success/failure feedback, and auto-generate prevention rules from repeated mistakes. Runs locally via ThumbGate MCP server.
Design patterns for building autonomous coding agents, including agent loops, tool-calling APIs, permission systems, and human-in-the-loop workflows.
<!-- AUTO-GENERATED by export-plugins.py — DO NOT EDIT -->