agentmods.dev

task

A command that sends a coding task, investigation, or follow-up request to a Kimi worker, an AI subagent. It can run the work in the foreground or background.

In plain words
What is it for?
Use it to delegate coding tasks, research, and follow-up work, with options to wait for the result, run it in the background, resume it, or select read-only mode.
Why use it?
It lets you hand off work to another AI worker without carrying out every step in the current session.

Command

2 1mo ago A scan 18 tokens copy · 88% MIT
View the source file satasuk03/kimi-plugin-cc
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/satasuk03/kimi-plugin-cc/task
Clone the repo
git clone --depth 1 https://github.com/satasuk03/kimi-plugin-cc
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 883 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00883
Opus 5 $0.00009 $0.00441
Sonnet 5 $0.00004 $0.00177
Haiku 4.5 $0.00002 $0.00088

Measured 2d ago against content hash a23e65094418, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

88% identical to rescue — 44 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/kimi/commands/task.md · 50 lines

What it actually says

Invoke the kimi:kimi-worker subagent via the Agent tool (subagent_type: "kimi:kimi-worker"), forwarding the raw user request as the prompt. kimi:kimi-worker is a subagent, not a skill — do not call Skill(kimi:kimi-worker) (no such skill) or Skill(kimi:task) (that re-enters this command and hangs the session). The command runs inline so the Agent tool stays in scope; forked general-purpose subagents do not expose it. The final user-visible response must be Kimi's output verbatim.

Raw user request: $ARGUMENTS

Execution mode:

  • If the request includes --background, run the kimi:kimi-worker subagent in the background.
  • If the request includes --wait, run the kimi:kimi-worker subagent in the foreground.
  • If neither flag is present, default to foreground.
  • --background and --wait are execution flags for Claude Code. Do not forward them to task, and do not treat them as part of the natural-language task text.
  • --model and --read-only are runtime-selection flags. Preserve them for the forwarded task call, but do not treat them as part of the natural-language task text.
  • If the request includes --resume, do not ask whether to continue. The user already chose.
  • If the request includes --fresh, do not ask whether to continue. The user already chose.
  • Otherwise, before starting Kimi, check for a resumable task thread from this Claude session by running:
node "${CLAUDE_PLUGIN_ROOT}/scripts/kimi-companion.mjs" task-resume-candidate --json
  • If that helper reports available: true, use AskUserQuestion exactly once to ask whether to continue the current Kimi thread or start a new one.
  • The two choices must be:
    • Continue current Kimi thread
    • Start a new Kimi thread
  • If the user is clearly giving a follow-up instruction such as "continue", "keep going", "resume", "apply the top fix", or "dig deeper", put Continue current Kimi thread (Recommended) first.
  • Otherwise put Start a new Kimi thread (Recommended) first.
  • If the user chooses continue, add --resume before routing to the subagent.
  • If the user chooses a new thread, add --fresh before routing to the subagent.
  • If the helper reports available: false, do not ask. Route normally.

Operating rules:

  • The subagent is a thin forwarder only. It should use one Bash call to invoke node "${CLAUDE_PLUGIN_ROOT}/scripts/kimi-companion.mjs" task ... and return that command's stdout as-is.
  • Return the Kimi companion stdout verbatim to the user.
  • Do not paraphrase, summarize, rewrite, or add commentary before or after it.
  • Do not ask the subagent to inspect files, monitor progress, poll /kimi:status, fetch /kimi:result, call /kimi:cancel, summarize output, or do follow-up work of its own.
  • Leave --read-only unset unless the user explicitly asks for read-only, investigation-only, or no-edits behavior.
  • Leave the model unset unless the user explicitly asks for one; when they do, pass the requested id through with --model <id>.
  • Leave --resume and --fresh in the forwarded request. The subagent handles that routing when it builds the task command.
  • If the helper reports that Kimi is missing or unauthenticated, stop and tell the user to run /kimi:setup.
  • If the user did not supply a request, ask what Kimi should investigate, build, or fix.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 50 lines · 18 tokens per session scan A a23e65094418

Subscribe to this mod's changes

task is a command published in the GitHub repository satasuk03/kimi-plugin-cc (2 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 883 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to rescue, differing in 44 lines, and is treated as a copy.

Building agentsPlanningResearchai-agentclaude-codeclaude-code-pluginclideveloper-toolskimi
Related

Other commands, from other repositories

swarm

Fan out a parallel review across the workspace using Kimi's AgentSwarm tool, bounded by a hard wall-clock budget. Read-only by default (enforced by the same PreToolUse hook as review, applied to every subagent); --write fans out edits in a throwaway worktree and returns a patch.

linxule/kimi-plugin-cc · 64 tokens

pursue

Hand Kimi an objective to pursue AUTONOMOUSLY across multiple turns (experimental goal mode), bounded by a hard wall-clock budget. Write-capable, gated by the same PreToolUse hook as rescue.

linxule/kimi-plugin-cc · 43 tokens

do

委派模型改文件/落盘/执行。隐含 --write(子进程获得 Edit/Write/Bash 全权)。主 Claude 会智能补 --with-context、选模型。.

alvis-HaoH/gkd · 42 tokens

workflow

把批量委派编排成 dynamic workflow——N 个 item 各派一个委派模型子进程并行处理。适合 50 个文件各转一次、N 个模块各审一次等同构批量。.

alvis-HaoH/gkd · 50 tokens

ask

委派模型回答/分析/审/咨询。只读不改文件(Read/Grep/Glob + Bash(git:))。主 Claude 会智能补 --with-context、选模型。.

alvis-HaoH/gkd · 43 tokens

brainstorm

多模型并行对同一问题各给独立意见(发散式 brainstorming),主 Claude 综合分歧、共识、独到见解。各模型彼此看不到对方答案,避免回声室效应。.

alvis-HaoH/gkd · 51 tokens