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/yuanlang12/kite/claude-mdgit clone --depth 1 https://github.com/yuanlang12/KiteWrote 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.
[](https://agentmods.dev/instructions/yuanlang12/kite/claude-md)<a href="https://agentmods.dev/instructions/yuanlang12/kite/claude-md"><img src="https://agentmods.dev/badge/instructions/yuanlang12/kite/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00554 | $0.00554 |
| Opus 5 | $0.00277 | $0.00277 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
Kite CLAUDE.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Kite is a Claude Code launcher that bridges your terminal session to IM platforms (Telegram, Feishu/Lark, WeChat, WeCom). It implements a mutual-exclusion state machine: at any moment, either the terminal OR an IM platform is controlling Claude. Both share the same session via --resume.
Communication Style
When discussing decisions with the project owner, use plain language that non-technical users can understand. Avoid jargon and technical terms — explain things in terms of user-facing behavior and outcomes.
Architecture
Core principle: Only one Claude process runs at a time. Local and remote modes never run simultaneously — switching kills the current process and starts a new one with --resume.
Single-process constraint: Each IM bot token can only be used by one kite process. Use multi-project routing (/addproject + /bind) to manage multiple projects from a single process.
Key design decisions:
- JSONL file watching — SessionScanner watches Claude Code's session files for real-time assistant message forwarding to IM
- Plugin architecture — Each IM platform is a separate package implementing
IMAdapterinpackages/<platform>/ - Zero infrastructure — Runs entirely locally, no external servers
- IM feedback layers — 👀 reaction on receipt, 🤔 thinking message edited to final response
- Binding gate — If registered projects exist and chat has no binding, messages are held until
/bind
Development Commands
bun install # Install dependencies
bun dev # Dev mode (apps/cli)
bun typecheck # Type check workspace
bun lint # Lint with Biome
bun format # Format with Biome (auto-fix)
Code Style
- Formatter/Linter: Biome (config in
biome.json) - Single quotes, no semicolons (
semicolons: asNeeded) - 2-space indentation, 100 char line width
- A PostToolUse hook auto-formats on every Write/Edit
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.
- 5d ago First seen · 58 lines · 554 tokens per session scan A 48dcd2c4e0a1
Kite CLAUDE.md is an instructions file published in the GitHub repository yuanlang12/Kite (19 stars, last pushed 3mo ago), licensed MIT. It adds 554 tokens to every session, about $0.0028 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 2026-08-30.
Other instructions, from other repositories
botmux CLAUDE.md
Claude Code instructions for deepcoldy/botmux, covering botmux, 构建 & 运行, bun 开发链路, worktree 的 nodemodules：共享还是独立（改前必读） and 编译态（单文件二进制）注意.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
nextclaw AGENTS.md
AGENTS.md instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.
bread CLAUDE.md
Instructions for tjakoen/bread, covering claude.md — start here, what this is, start here (reading order), this repo is the stack's control plane — run it and non-negotiables (see conventions for the full rules).
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
rosetta command-versions-vs-presence.instructions.md
Instructions for tikoci/rosetta, a project described as: MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik.