feedback_summary
2 registry entries were observed exposing a tool named feedback_summary — none of them flagged as a privileged capability.
Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 12,342 of 40,590 scannable entries (30%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.
- v1.27.17↓ 1k/wk
ThumbGate self-improving agent governance: thumbs-up/down turns every mistake into a prevention rule and blocks repeat patterns. 36 pre-action checks, budget enforcement, and self-protection for Claude Code, Cursor, Codex, Gemini CLI, and Amp.
ClaudeCursorCopilotGeminimcpmcp-serverai-agentsagent-skillsskillcontext-engineering - v0.7.4★ 26
Pre-action gates that block AI agents from repeating known mistakes.
ClaudeCursorCopilotGeminimcp