From kimi
Offloads complex multi-step debugging, implementation, and refactoring tasks to Kimi's isolated runtime. Proactive handoff preserves main context. Use @kimi-rescue for work too large for inline response.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
kimi:agents/kimi-rescuesonnetThe summary Claude sees when deciding whether to delegate to this agent
Route suitable delegated implementation and debugging work into the shared companion runtime without becoming a second orchestrator. <example> Context: The user says, "Hand this flaky integration failure to Kimi and have it investigate in the background." Why this triggers: The user is explicitly delegating a substantial debugging task rather than asking for a review or a small inline answer. <...
Route suitable delegated implementation and debugging work into the shared companion runtime without becoming a second orchestrator.
Context: The user says, "Hand this flaky integration failure to Kimi and have it investigate in the background." Why this triggers: The user is explicitly delegating a substantial debugging task rather than asking for a review or a small inline answer. Context: The user says, "Ask Kimi to do a cross-file pass on this auth refactor and try the smallest safe fix." Why this triggers: The task is multi-file, implementation-oriented, and better handled as an offloaded rescue run. Context: The user says, "Have Kimi keep going from the last rescue and apply the top fix." Why this triggers: The user is clearly asking to resume a prior Kimi rescue workflow. Context: The main Claude thread has been debugging a multi-file runtime error for several turns, the investigation has grown beyond inline reasoning, and the user has not yet explicitly asked for delegation. Why this triggers: The task has outgrown the main thread's context; proactive rescue handoff preserves the user's attention and offloads the deep search into an isolated Kimi session.When invoked:
job_id so the main thread can use /kimi:status, /kimi:result, or /kimi:cancel/kimi:result <jobId> --json returns a structured envelope with metadata plus the artifact body.When rescue completes:
Do not do repository discovery before forwarding, do not implement your own polling loop, and do not turn rescue into a separate planning agent.
Surgical 1-2 file editor for typo fixes, single-function rewrites, mechanical renames, comment removal, format tweaks. Refuses 3+ files, new features, cross-file changes. Returns caveman diff receipt.
Trains, evaluates, and ships RuView models: WiFlow pose, camera-supervised pose, RuVector embeddings, domain generalization, and SNN adaptation. Handles GPU training on GCloud and Hugging Face publishing.
npx claudepluginhub linxule/kimi-plugin-cc --plugin kimi