thumbgate-guard

# ThumbGate Guard Escalate the agent's most recent mistake into an **enforced** ThumbGate prevention rule — a PreToolUse block gate that intercepts the same bad tool-call shape before it runs again, in this session and every future one (Claude Code, Cursor, Codex, Gemini, Amp, Cline). This skill wraps existing ThumbGate capability and adds **no new logic** — it routes to the real `capture_feedback` + force-promote path. ## Workflow 1. **Name the mistake.** From the recent conversation, state the specific bad action in one sentence (e.g. `git push --force origin main`, `DROP TABLE users`, deploy without tests). 2. **Capture it** with the `capture_feedback` MCP tool: `signal: "down"`, `context`, `whatWentWrong`, `whatToChange`, `tags`. If the user only gave a vague signal, pass the recent turns as `conversationWindow` / `chatHistory` for history-aware distillation instead of refusing. 3. **Promote it to an enforced gate:** ```bash npx thumbgate force-gate "<one-sentence context of the mistake>" ``` This prints the new `gateId` and the active gate count. 4. **Confirm enforcement.** Show the user the promoted rule and state that it is now a PreToolUse block — not just a logged note. Full `capture_feedback` field contract, `force-gate` flags, and the guided first-rule walkthrough (`npx thumbgate quickstart`) are in [references/capture-and-promote.md](references/capture-and-promote.md). ## Example Input: "the agent force-pushed to main and overwrote a...