القائمة
Nested shell-manual reference for Kimi Code CLI. Read this when you need to run, validate, or document `kimicode / kimi` as a long-running shell subprocess or LingTai daemon harness candidate.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Read-only health diagnostics for LingTai agents and bots. Use when an agent appears offline or unreachable, when a machine migration may have left stale MCP/addon command paths, when heartbeat/status/process/notification/log surfaces disagree, or before deciding whether to mail, refresh, CPR, or edit persistent configuration. Includes a bundled doctor.py script for layered local checks without exposing secrets.
Complete catalogue of environment variables consumed by the LingTai kernel, wrapper, bundled MCPs, adapters, tests, and daemon composition surfaces.
Second-layer router for LingTai's progressive-disclosure operating manuals. Read this when resident substrate/procedures are too compact and you need the right lower reference. Route here for the expanded substrate/runtime model, lifecycle and `system` tool actions, the init.json composition and preset runtime model route, action/procedure discipline and skill routing, tool-result summarization, SQLite/`log.sqlite` trace inspection and trajectory mining, runtime/kernel update checks and nudges, environment variables, goal notifications, molt/memory questions, MCP/addon ownership, collaboration topology, and resident prompt design. The nested catalog below names each reference and its exact trigger.
Mandatory repository-local development guide for LingTai's Python kernel and runtime. Use this before changing code, architecture documents, tests, packaging, capabilities, adapters, or developer documentation in lingtai-kernel. Routes each task through the exact baseline, the distributed ANATOMY/CONTRACT systems, focused validation, and pull-request safety gates.
Operational guide for LingTai's built-in file tools: read, write, edit, glob, and grep. Use when working with local text files, deciding whether to use file tools versus bash, handling large files, avoiding binary/image misuse, or reading non-UTF-8 text via explicit bash/Python/iconv instead of complicating the core read tool. Covers UTF-8 policy, safe write/edit discipline, search workflows, and examples for GBK/Shift-JIS/Latin-1 conversion.
Router for LingTai's distributed code navigation system. Use this before navigating, creating, or maintaining kernel ANATOMY.md files. The normative anatomy-of-anatomy now lives at the repository-root ANATOMY.md; this skill explains how an agent enters and descends that graph, how it pairs with the distributed CONTRACT.md interface-definition graph, and what to do when code and navigation disagree.
| name | bash-kimicode |
| description | Nested shell-manual reference for Kimi Code CLI. Read this when you need to run, validate, or document `kimicode / kimi` as a long-running shell subprocess or LingTai daemon harness candidate. |
| version | 0.1.0 |
| last_changed_at | "2026-07-19T00:00:00.000Z" |
| related_files | ["src/lingtai/tools/bash/manual/SKILL.md","src/lingtai/tools/daemon/manual/reference/cli-backends/reference/backends/kimicode/SKILL.md"] |
| maintenance | Tracks the Kimi Code CLI backend/topic behavior it documents; update when that integration changes. |
Nested shell-manual reference. Read shell-manual ## Coding-CLI harness baseline first — it owns the shared run---help-before-you-rely rule, the
CLI-vs-daemon choice, the candidate-harness promotion criteria, and the generic
validation checklist. This page adds only what is specific to this CLI.
Use for MoonshotAI Kimi Code subprocesses (official MoonshotAI/kimi-code
single binary kimi, version observed 0.22.3 for MCP config support). Keep
provider/model credential discovery elsewhere; this page only owns shell
execution hygiene.
kimi --prompt '<prompt>' --output-format text
text or stream-json via --output-format (note: it is
--output-format, not --format).-m/--model <model>.--prompt with --yolo — the CLI refuses that pairing.--prompt / --output-format and forbids --yolo;
free-form backend_options are inserted before those owned flags.The daemon backend sets per run (never logging secret values):
KIMI_CODE_HOME — a run-private directory so concurrent runs don't share state.KIMI_DISABLE_TELEMETRY=1, KIMI_CODE_NO_AUTO_UPDATE=1.KIMI_MODEL_API_KEY — mapped from the first set of KIMICODE_API_KEY /
KIMI_API_KEY / MOONSHOT_API_KEY, only when not already set.KIMI_MODEL_NAME / KIMI_MODEL_PROVIDER_TYPE / KIMI_MODEL_BASE_URL /
KIMI_MODEL_MAX_CONTEXT_SIZE — provider defaults, applied only when absent.Kimi Code's installed 0.22.3 bundle lists MCP declaration targets at
$KIMI_CODE_HOME/mcp.json, project-root .mcp.json, and cwd-local
.kimi-code/mcp.json. Its MCP schema accepts transport: "stdio" with
command/args/env and transport: "http" with url/headers (plus SSE,
which LingTai daemon task registrations do not expose). The daemon uses only the
run-private $KIMI_CODE_HOME/mcp.json path so each emanation gets isolated
native MCP config.
--prompt + --output-format text).ask/resume is not supported yet: -S/--session and -c/--continue
exist, but a stable machine-readable session-id output was not verified, so a
reliable resume contract could not be source-cited. daemon(action='ask')
returns an explicit unsupported-backend error.$KIMI_CODE_HOME/mcp.json: daemon_common plus parent-provided stdio and HTTP
MCP registrations are native tools for this backend. Prompt and durable
daemon.json contexts still redact env/headers values; the unredacted
values live only in the native per-run config.Run the baseline checklist, with these substitutions:
--yolo conflicts with --prompt.ask, source-cite a stable session-id output plus a tested
resume command from local help/code — do not guess.