A command that sends a task specification file to Kimi's coding agent for implementation. It can continue an earlier session, start a fresh one, select a model, and run review checks around the work.

Use it to execute task files, resume or restart delegated work, choose a Kimi model, enable background execution, or request plan and diff reviews.

It organizes delegated coding around a written task and adds pre-flight checks for repository state and task validation before execution.

kimi:crank — Command for Claude Code by luanmorenommaciel

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.

Clone the repo

git clone --depth 1 https://github.com/luanmorenommaciel/kimi-plugin-cc

Made for: Claude Code.

Or install kimi, the plugin that ships this one along with the rest of its 2 skills, 12 commands, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/luanmorenommaciel/kimi-plugin-cc/kimi-crank/github.svg)](https://agentmods.dev/commands/luanmorenommaciel/kimi-plugin-cc/kimi-crank)

Your own site

<a href="https://agentmods.dev/commands/luanmorenommaciel/kimi-plugin-cc/kimi-crank"><img src="https://agentmods.dev/badge/commands/luanmorenommaciel/kimi-plugin-cc/kimi-crank/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/luanmorenommaciel/kimi-plugin-cc/kimi-crank"><img src="https://agentmods.dev/badge/commands/luanmorenommaciel/kimi-plugin-cc/kimi-crank.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,414 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.01414
Opus 5	$0.00018	$0.00707
Sonnet 5	$0.00007	$0.00283
Haiku 4.5	$0.00004	$0.00141

Measured 10d ago against content hash 5555f0c425e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kimi:crank 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 10d 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/commands/kimi:crank.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/kimi:crank

Delegate a task to Kimi's coder agent. Captures diff and returns a session ID.

Usage

/kimi:crank tasks/T-20260526-build-kimi-plugin-cc.md
/kimi:crank tasks/T-20260526-build-kimi-plugin-cc.md --background
/kimi:crank tasks/T-20260526-build-kimi-plugin-cc.md --model kimi-code/k3
/kimi:crank --resume                # continue latest session for this repo
/kimi:crank --fresh                 # start new session, ignore latest
/kimi:crank task.md --auto-commit on-clean
/kimi:crank task.md --plan-review --diff-review

Process

Validate input
- Check that the argument path exists and matches tasks/T-*.md pattern.
- Handle --resume: continue the latest repo session natively — the broker passes the stored Kimi session id via kimi --session <id>.
- Handle --fresh: ignore the latest session and start clean (--fresh and --resume are mutually exclusive).
Pre-flight gates
- Origin-state check: fetch origin, abort if touched paths diverged (override with --force-dispatch).
- Preflight eval check: run task-spec validator, abort if evals are buggy (override with --skip-preflight).
- Context injection: prepend CLAUDE.md / AGENTS.md / scoped rules (disable with --no-context).
Optional Codex review
- --plan-review: adversarial plan critique before dispatch.
- --diff-review: adversarial diff review before commit.
Read task file
```
Read(<task-path>)
```

Capture pre-run diff

Bash("node plugins/kimi/scripts/broker.mjs diff-capture --session-id <id> --phase pre")

Dispatch to Kimi via broker

Bash("node plugins/kimi/scripts/broker.mjs dispatch \
  --prompt '<task_content>' \
  --role coder \
  --session-id <id> \
  --mode crank \
  --task-path <task-path> \
  --touches-paths <csv-from-spec> \
  [--background] \
  [--model <model>] \
  [--effort low|medium|high|xhigh|max] \
  [--auto-commit on|off|on-clean]")

Always pass --task-path and --touches-paths — omitting them silently disables the origin-divergence check, the preflight buggy-evals gate, context injection, research/patterns/deep-research injection, and --plan-review.

Read the full file on GitHub · 105 lines

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.

10d ago First seen · 105 lines · 36 tokens per session scan A 5555f0c425e3

Subscribe to this mod's changes

kimi:crank is a command published in the GitHub repository luanmorenommaciel/kimi-plugin-cc (12 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,414 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.

Building agents

kimi:crank

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/kimi:crank

Usage

Process

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement