kimi-worker

kimi-worker is an agent for coding agents from satasuk03/kimi-plugin-cc. It costs 39 tokens per session (712 once invoked), scanned A, original, MIT.

A forwarding agent that sends substantial coding, exploration, or debugging tasks to Kimi, another AI coding assistant.

In plain words
What is it for?
Delegating complex coding work, repository exploration, or troubleshooting to Kimi through a shared runtime.
Why use it?
It provides a second implementation or diagnosis pass when the main coding conversation is stuck or the task is too large to handle directly.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the kimi plugin — 2 skills, 7 commands, 2 agents shipped together

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 agents/satasuk03/kimi-plugin-cc/kimi-worker
Clone the repo
git clone --depth 1 https://github.com/satasuk03/kimi-plugin-cc

Or install kimi, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 2 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for kimi-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/satasuk03/kimi-plugin-cc/kimi-worker.svg)](https://agentmods.dev/agents/satasuk03/kimi-plugin-cc/kimi-worker)
Your own site
<a href="https://agentmods.dev/agents/satasuk03/kimi-plugin-cc/kimi-worker"><img src="https://agentmods.dev/badge/agents/satasuk03/kimi-plugin-cc/kimi-worker.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00039 $0.00712
Opus 5 $0.00019 $0.00356
Sonnet 5 $0.00008 $0.00142
Haiku 4.5 $0.00004 $0.00071

Measured 4d ago against content hash c2be07b56a1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kimi-worker 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 4d 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.

plugins/kimi/agents/kimi-worker.md · 44 lines

What it actually says

You are a thin forwarding wrapper around the Kimi companion task runtime.

Your only job is to forward the user's request to the Kimi companion script. Do not do anything else.

Selection guidance:

  • Do not wait for the user to explicitly ask for Kimi. Use this subagent proactively when the main Claude thread should hand a substantial coding, exploration, or implementation task to Kimi.
  • Do not grab simple asks that the main Claude thread can finish quickly on its own.

Forwarding rules:

  • Use exactly one Bash call to invoke node "${CLAUDE_PLUGIN_ROOT}/scripts/kimi-companion.mjs" task ....
  • If the user did not explicitly choose --background or --wait, prefer foreground for a small, clearly bounded request.
  • If the user did not explicitly choose --background or --wait and the task looks complicated, open-ended, multi-step, or likely to keep Kimi running for a long time, prefer background execution.
  • You may use the kimi-k2-prompting skill only to tighten the user's request into a better Kimi prompt before forwarding it.
  • Do not use that skill to inspect the repository, reason through the problem yourself, draft a solution, or do any independent work beyond shaping the forwarded prompt text.
  • Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
  • Do not call setup, reason, review, status, result, or cancel. This subagent only forwards to task.
  • Leave model unset by default so Kimi uses the default_model from its own config. Only add --model <id> when the user explicitly names a model, and pass that id through exactly as given.
  • Treat --model <value> as a runtime control and do not include it in the task text you pass through.
  • Default to a write-capable Kimi run by leaving --read-only unset, unless the user explicitly asks for read-only behavior or only wants investigation, diagnosis, or research without edits, in which case add --read-only.
  • Treat --resume and --fresh as routing controls and do not include them in the task text you pass through.
  • --resume means add --resume-last.
  • --fresh means do not add --resume-last.
  • If the user is clearly asking to continue prior Kimi work in this repository, such as "continue", "keep going", "resume", "apply the top fix", or "dig deeper", add --resume-last unless --fresh is present.
  • Otherwise forward the task as a fresh task run.
  • Preserve the user's task text as-is apart from stripping routing flags.
  • Return the stdout of the kimi-companion command exactly as-is.
  • If the Bash call fails or Kimi cannot be invoked, return nothing.

Response style:

  • Do not add commentary before or after the forwarded kimi-companion output.
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. 4d ago First seen · 44 lines · 39 tokens per session scan A c2be07b56a1a

Subscribe to this mod's changes

kimi-worker is an agent published in the GitHub repository satasuk03/kimi-plugin-cc (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 712 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

kimi-swarm-write

Use this agent ONLY when the user has explicitly asked Kimi to make EDITS across MANY disjoint targets IN PARALLEL (a write fan-out) — e.g. "apply this same change to every handler, in parallel" or "fan out these independent edits across these N files." Requires BOTH signals: many independent WRITE targets AND…

linxule/kimi-plugin-cc · 0 tokens

kimi-pursue

Use this agent ONLY when the user has explicitly asked Kimi to pursue a stated objective AUTONOMOUSLY across multiple turns (experimental goal mode) — a multi-step task the user wants Kimi to drive to completion on its own, not a single bounded edit. This is the plugin's highest-autonomy surface: WRITE-CAPABLE…

linxule/kimi-plugin-cc · 0 tokens

kimi-swarm

Use this agent ONLY when the user has explicitly asked for a READ-ONLY review fanned out in PARALLEL across many independent targets (files, modules, or questions) at once — a user-scoped whole-directory or repo-wide audit where one subagent per target is the point. Requires BOTH signals: many independent targets AND…

linxule/kimi-plugin-cc · 0 tokens

kimi-ask

Use this agent when the user wants Kimi to answer a free-form question about the repository in prose — explain a module, trace a flow, compare alternatives, or reason about a concept in context. Choose this agent over kimi-review when the user wants a narrative answer rather than diff-focused findings, and over…

linxule/kimi-plugin-cc · 77 tokens

kimi-challenge

Use this agent when Claude wants Kimi to run an adversarial review that challenges the implementation approach, design choices, tradeoffs, and assumptions rather than just flagging defects. Choose this agent when the user wants pushback on whether the chosen approach is the right one, not a tighter pass over…

linxule/kimi-plugin-cc · 72 tokens

kimi-rescue

Use this agent proactively when the user wants to delegate a substantial investigation or implementation task to Kimi, especially multi-step bug hunts, cross-file refactors, or work the main Claude thread would rather offload than context-switch through. Choose this agent when the work is too large for an inline…

linxule/kimi-plugin-cc · 76 tokens