A command that checks whether Kimi Code is installed, authenticated, configured with its supporting services, and ready to use. Kimi Code is an external coding agent that can be assigned development tasks.

Use it to verify the Kimi Code version, authentication, configured MCP servers, role prompts, review gate, and AFK defaults.

It identifies missing installations, login problems, damaged role prompts, and configuration issues before you depend on Kimi Code.

kimi:setup — 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-setup.svg)](https://agentmods.dev/commands/luanmorenommaciel/kimi-plugin-cc/kimi-setup)

Your own site

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

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 889 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	$0.00026	$0.00889
Opus 5	$0.00013	$0.00445
Sonnet 5	$0.00005	$0.00178
Haiku 4.5	$0.00003	$0.00089

Measured 6d ago against content hash 1c4ac4452570, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

kimi:setup 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 6d 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:setup.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/kimi:setup

Verify the Kimi Code 0.x installation, auth, MCP config, and configure the review gate and AFK defaults.

Process

Run the broker doctor
```
Bash("node plugins/kimi/scripts/broker.mjs doctor")
```
This reports, as JSON: binary generation + version, kimi doctor config validation, auth state (no quota spent), configured MCP servers, and role-prompt availability.
Interpret the binary check
- generation: "kimi-code" (0.x) → OK.
- generation: "legacy" (1.x) → tell the user to migrate: npm i -g @moonshot-ai/kimi-code, or run /upgrade inside the legacy CLI (it migrates config and sessions automatically).
- generation: "missing" → install Kimi Code: npm i -g @moonshot-ai/kimi-code (or the native installer from https://www.kimi.com/code), then kimi login.
Interpret auth
- auth.ok: false → instruct the user to run !kimi login (device-code flow, no TUI needed).
Interpret MCP + roles
- Report the configured MCP server count and names.
- roles.ok: false means the plugin install is damaged — recommend reinstalling the plugin.
Review gate toggle (if flags provided)
```
Bash("node plugins/kimi/scripts/broker.mjs review-gate --enable")
Bash("node plugins/kimi/scripts/broker.mjs review-gate --disable")
Bash("node plugins/kimi/scripts/broker.mjs review-gate")   # status
```
- The gate wires a real Claude Code Stop hook running scripts/review-gate.mjs, which asks Kimi to sanity-check each proposed response and blocks the stop on critical findings. It is fail-open (hook errors never block).
- After enabling or disabling, tell the user to run /reload-plugins (or restart Claude Code) — hooks.json is only read at plugin-load time. Updating or reinstalling the plugin resets the gate to off (the shipped hooks.json is {"hooks": {}}).
- The gate runs Kimi read-only (prompt-level constraint: no file writes, no mutating commands, no subagents) at low thinking effort. KIMI_REVIEW_GATE_MODEL overrides the model, KIMI_REVIEW_GATE_TIMEOUT_MS the timeout.
- Loop safeguards: the gate exits immediately when the Stop payload has stop_hook_active, and a circuit breaker allows the stop after 3 consecutive blocks for the same Claude session (KIMI_REVIEW_GATE_MAX_BLOCKS to override).

Read the full file on GitHub · 67 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.

6d ago First seen · 67 lines · 0 tokens per session scan A 1c4ac4452570

Subscribe to this mod's changes

kimi:setup is a command published in the GitHub repository luanmorenommaciel/kimi-plugin-cc (10 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 889 once invoked, about $0.0001 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.

kimi:setup

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:setup

Process

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement