kimi-cli-runtime

kimi-cli-runtime is a skill for Claude Code from luanmorenommaciel/kimi-plugin-cc. It costs 0 tokens per session (462 once invoked), scanned A, original, MIT.

Reference instructions for running the Kimi Code command-line tool without an interactive terminal and reading its JSON-lines output.

In plain words
What is it for?
Use them when another plugin needs to start Kimi for a prompt, select a model, continue a session, parse results, or respond to its exit codes.
Why use it?
They prevent use of unsupported command options and explain how to resume sessions, handle failures, and retry temporary errors.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the kimi plugin — 2 skills, 12 commands, 1 agent shipped together

Good fit Use them when another plugin needs to start Kimi for a prompt…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/luanmorenommaciel/kimi-plugin-cc/kimi-cli-runtime
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.

Any agent
npx skills add luanmorenommaciel/kimi-plugin-cc --skill kimi-cli-runtime
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.

agentmods badge for kimi-cli-runtime

README.md
[![agentmods](https://agentmods.dev/badge/skills/luanmorenommaciel/kimi-plugin-cc/kimi-cli-runtime.svg)](https://agentmods.dev/skills/luanmorenommaciel/kimi-plugin-cc/kimi-cli-runtime)
Your own site
<a href="https://agentmods.dev/skills/luanmorenommaciel/kimi-plugin-cc/kimi-cli-runtime"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/kimi-plugin-cc/kimi-cli-runtime.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 462 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00462
Opus 5 $0.00000 $0.00231
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 7d ago against content hash d20fb3a2615b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

kimi-cli-runtime 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 7d 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/skills/kimi-cli-runtime/SKILL.md · 43 lines

What it actually says

Kimi CLI Runtime

Reference skill for the kimi-plugin-cc plugin. Documents how the Kimi Code 0.x CLI is invoked in headless mode.

Headless invocation

kimi -p "<prompt>" --output-format stream-json [--model <alias>]

The working directory is set via the spawn cwd — there is no --work-dir flag. Do NOT pass --yolo: prompt mode already runs under auto permission, and 0.x rejects the --yolo + -p combination.

Flags

Flag Description
-p "<text>" Run one prompt non-interactively
--output-format stream-json JSONL output (one JSON per line)
--model <alias> Override model (e.g. k3)
--session <id> Resume a previous Kimi session natively
--continue Continue the most recent session for the working directory

Legacy 1.x flags that no longer exist and must never be emitted: --print, --quiet, --work-dir, --agent-file.

Exit codes

Code Meaning Action
0 Success Proceed
1 Permanent failure Fail fast
75 Transient failure Retry with backoff (max 3)

Broker-level dispatch exit codes (2 origin-diverged, 3 buggy-evals, 4 review-pause, 5 checkpoint-conflict, 6 timeout) are documented in agents/kimi-delegate.md.

Roles (replaces agent files)

Roles are Markdown system prompts under plugins/kimi/roles/, composed into the head of the -p prompt by the broker:

  • coder — general software engineering (read/write/shell)
  • explore — read-only codebase exploration (prompt-level constraint; 0.x cannot exclude tools headlessly)

Built-in Kimi Code subagents (coder, explore, plan) are scheduled by the Kimi agent itself inside the session — the broker does not select them.

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. 7d ago First seen · 43 lines · 0 tokens per session scan A d20fb3a2615b

Subscribe to this mod's changes

kimi-cli-runtime is a skill published in the GitHub repository luanmorenommaciel/kimi-plugin-cc (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 462 tokens. 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens