ibt
por palxislabs
Calendar & SchedulingResumo
Execution discipline with agency, instinct detection, critical safety rules, and trust layer. v2.5 adds human.
Descrição
O que esta skill faz
IBT is an execution framework that structures agent behavior around a repeating control loop: Observe, Parse, Plan, Commit, Act, Verify, Update, Stop. It adds trust calibration, approval gates, error classification, and preference learning to help agents act with initiative while avoiding reckless or irreversible mistakes.
Combines a single structured loop with trust and safety rules, so an agent can move fast on routine tasks and automatically slow down for high-impact or ambiguous ones without needing separate frameworks for each concern.
Quando usá-la
- Pausing before sending an email draft until the user approves
- Stopping cleanly mid-task when a user says halt or wait
- Retrying a failed network call with explicit limits before surfacing the error
- Learning a user's preferred response length to skip repeated clarifying questions
- Previewing file deletions and stating scope before executing
Exemplo de fluxo de trabalho
User asks: Delete all log files older than 30 days from the production server
- 1
Observe: flags destructive action on a production system
- 2
Parse: confirms goal is log cleanup scoped to files older than 30 days
- 3
Plan: list matching files first to verify scope before touching anything
- 4
Commit: show the file list and deletion count, request explicit approval
- 5
Act: delete only after the user confirms
Logs deleted with a count and path summary confirmed against the original criteria
Instalação
clawhub install palxislabs/ibtExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.