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.
npx agentmods add instructions/userfrm/kimi-code-mcp/claude-mdgit clone --depth 1 https://github.com/userFRM/kimi-code-mcpWhat 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 | $0.00908 | $0.00908 |
| Opus 5 | $0.00454 | $0.00454 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
kimi-code-mcp CLAUDE.md scanned grade A with 1 finding 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 2d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Tests use vitest with `vi.mock` for child_process and fs mocking How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
kimi-code-mcp is an MCP (Model Context Protocol) server that wraps the Kimi Code CLI (kimi-k2.5). It exposes 14 tools over stdio for filesystem, shell, web, and agent operations.
Architecture
4 source files, no external runtime dependencies beyond @modelcontextprotocol/sdk and zod:
src/
index.ts — MCP server entry point (shebang, stdio transport, zodToJsonSchema, request handlers)
handlers.ts — TOOLS array (14 tool definitions with Zod schemas), TOOL_MAP, handleToolCall, buildPrompt
cli.ts — findKimiCli, buildKimiArgs, executeKimi (spawns kimi CLI as child process)
parser.ts — parseKimiOutput, extractTextParts, extractThinkParts, extractPlainText
Data flow: MCP request → index.ts validates with Zod → handleToolCall in handlers.ts builds a natural language prompt → executeKimi in cli.ts spawns kimi --print -y -p <prompt> → parser.ts extracts TextPart/ThinkPart from CLI output → result returned as MCP text content.
Key Design Decisions
- No shell execution in spawn:
cli.tsusesspawn(binary, argsArray)with noshell: true— prevents command injection. - Single-pass regex for unescaping:
parser.tsusesstr.replace(/\\(\\|n|'|")/g, ...)instead of chained.replace()calls to avoid ordering bugs (e.g.,\\nmust stay as literal backslash-n, not become a newline). - Timeout double-reject guard:
executeKimiuses akilledflag so thecloseevent handler no-ops after a timeout kill. zodToJsonSchemais inlined: A minimal Zod-to-JSON-Schema converter lives inindex.ts— handles string, number, boolean, enum, optional, and.describe(). No need for a full library.KIMI_CLI_PATHmust be absolute: Usespath.isAbsolute()to reject relative paths.
Build & Test
npm install
npm run build # tsc → dist/
npm test # vitest run (68 tests)
Tests live in src/__tests__/. Test files are excluded from tsconfig.json and the npm tarball.
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.
- 2d ago First seen · 60 lines · 908 tokens per session scan A 51528ea55465
kimi-code-mcp CLAUDE.md is an instructions file published in the GitHub repository userFRM/kimi-code-mcp (7 stars, last pushed 2mo ago), licensed MIT. It adds 908 tokens to every session, about $0.0045 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.