Run a write-capable Kimi swarm that edits many disjoint targets in a throwaway worktree and returns a reviewable patch. Use only for explicit parallel edit fan-out requests; the plugin never applies or commits the patch.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Forward this request to the local kimi-code companion runtime by shell. Do not use MCP for this skill.
$PLUGIN_ROOT if the host sets it; otherwise use the directory that CONTAINS the skills/ directory (i.e. two levels up from this SKILL.md).<plugin-root>/scripts/companion.sh must exist — it is the bundled entrypoint that resolves Node and runs the compiled runtime from <plugin-root>/dist/.scripts/companion.sh captures the intended workspace cwd.PLUGIN_ROOT="<plugin-root>" "<plugin-root>/scripts/companion.sh" task swarm --write <args>CLAUDE_PLUGIN_DATA/PLUGIN_DATA against this package's own host-specific directory. On PLUGIN_DATA_CONFLICT, surface the error; do not automatically choose a new store or copy data. An explicit absolute KIMI_PLUGIN_CC_DATA selects a custom data parent (the runtime appends kimi-plugin-cc/). Checkouts retain unambiguous legacy variables and the Codex fallback under CODEX_HOME or HOME; a launch with no home needs an explicit data root.Pass through: [--budget <30m|1h>] [--cap <N>] [--max-concurrency <N>] [-m <model>] [--thinking <effort>] <objective>
--thinking <effort> requests one for this run (honoured by Kimi's own providers on models that can turn thinking off; other providers ignore it silently; the plugin cannot verify it). Preserve --thinking <effort> or --thinking=<effort>; --no-thinking is rejected, use --thinking off. Omission preserves ambient operator env; resumes do not inherit previous job effort. Status and result --json report thinking_effort_requested, not observed effort.hook_escapes array in result <jobId> --json (or a safety hook notice on stderr) is detection evidence, not a failure: a policy-denied tool call came back as something other than the managed hook's denial — an upstream pre-hook rejection, another hook blocking first, or hook drift. Surface it to the user and suggest /kimi:setup --check; never treat the job as failed or retry on its own.-m: fresh sessions use Kimi's configured default (including its environment overlay), and resumed sessions keep their session model. Never change the saved default for a one-off request.-m/--model alias. For a natural-language model/provider request, first run the same companion entrypoint with setup --models --json; match the requested alias, model ID or provider to exactly one configured model. If ambiguous, ask the user to choose; if missing or incomplete, stop and guide native provider setup. Never guess an alias or silently fall back after a model/auth error. A model merely mentioned as the subject of a question is not a selection request.-m argument. The inventory is not a connection test; never claim configured means authenticated or working. Do not run kimi provider list --json, read raw config/credentials, or request API keys in chat./login; for API keys or other providers, guide native /provider and have the user enter secrets there. Only an explicit saved-default request calls for native /model. Re-list after setup; use setup --check for hook readiness. Swarm -m selects the coordinator; [secondary_model] can select different child models.--max-concurrency conservative, normally 1, unless the user explicitly asks to widen it.--background, but detaching your own shell call is expected: a fan-out routinely outlives a foreground timeout, and the run is patch-only and worktree-confined. Keep --budget and --max-concurrency finite. To stop a run, use companion.sh cancel with NO id — it targets the latest running job for the repo, and no UUID crosses you or the user (a detached run prints nothing at launch; the id first arrives with the final report). Prefer that over an interrupt: an interrupt gives the companion only ~1.35s before SIGKILL, less than its teardown plus git diff --binary patch capture, so interrupting can lose the patch.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Ask Kimi a read-only free-form question about the current repository. Use for prose explanations, flow tracing, module comparisons, or conceptual reasoning where Codex should delegate the answer to local kimi-code rather than perform implementation.
The English summary is being prepared. Showing the original description.
Cancel an active plugin-managed Kimi job for the current repository. Use only when the user explicitly asks to cancel a Kimi run.
The English summary is being prepared. Showing the original description.
Run a read-only adversarial Kimi challenge review that questions assumptions, design choices, and tradeoffs. Use when the user wants pushback on whether the approach is right, not a defect-only review.
The English summary is being prepared. Showing the original description.
Run Kimi's autonomous goal mode for an explicitly requested hands-off multi-turn objective. This is write-capable and budget-bounded; use only when the user explicitly asks Kimi to pursue an objective autonomously.
The English summary is being prepared. Showing the original description.
Re-render a stored event log for a completed plugin-managed Kimi job. Use only when the user explicitly asks to replay a Kimi job.
The English summary is being prepared. Showing the original description.
Delegate a bounded write-capable investigation or implementation task to Kimi through the companion runtime. Use only when explicitly invoked or when the user clearly asks to hand off a substantial fix to Kimi.
The English summary is being prepared. Showing the original description.