USE when diagnosing component failures, hallucinations, or instruction drift. Performs forensic investigation of session logs, scratchpads, and tool prompts to apply permanent fixes.
/plugin marketplace add Git-Fg/thecattoolkit/plugin install sys-core@cattoolkitThis skill is limited to using the following tools:
assets/scripts/bootstrap.shreferences/bootstrap-protocol.mdreferences/diagnosis-patterns.mdYou MUST first resolve the user's input to a concrete file path:
find_by_name to locate the SKILL.md or component definition.plugins/ that matches the component type (Agent, Skill, Command).You MUST analyze the "Black Box" of the failure by reading the following state files:
.cattoolkit/context/context.log (Find the exact timestamp of the error)..cattoolkit/context/scratchpad.md (Check the agent's intent vs. its tool usage).hooks/hooks.json (Verify if a hook intercepted the tool call).SKILL.md, agent.md, or command.md.Compare the Tool Prompt (from context.log) against the Instructions (from the manifesto).
block status that the agent didn't handle.DO NOT revert files. Update the logic to be more resilient:
## Constraints section with specific MUST NOT instructions addressing the error.Update the component's Description keywords to better match its actual successful triggers, and add a "Troubleshooting" section to the bottom of the component's file documenting this fix.