What is claude-lark-plugin CLAUDE.md?

A set of instructions for the Claude Lark Plugin, which connects Claude Code to Feishu/Lark messaging through a live connection. It documents the project layout, commands, and key design choices.

Use it when developing, testing, or troubleshooting the plugin's messaging channel, memory features, and related tools.

It gives an agent the project context needed to change the plugin without breaking its message flow or configuration.

How IS908/claude-lark-plugin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to IS908/claude-lark-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/IS908/claude-lark-plugin/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/IS908/claude-lark-plugin

Made for: Claude Code.

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/instructions/is908/claude-lark-plugin/claude-md/github.svg)](https://agentmods.dev/instructions/is908/claude-lark-plugin/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/is908/claude-lark-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/is908/claude-lark-plugin/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/is908/claude-lark-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/is908/claude-lark-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,085 This file is loaded in full into every session.

When invoked 4,085 The same file — it is already loaded in full.

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	$0.04085	$0.04085
Opus 5.5	$0.01634	$0.01634
Sonnet 5.5	$0.00817	$0.00817
Haiku 4.5	$0.00409	$0.00409

Measured 2mo ago against content hash c5dcb0b744e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-lark-plugin 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 2mo 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.

CLAUDE.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 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

Claude Lark Plugin is an MCP (Model Context Protocol) channel plugin that connects Claude Code to Feishu/Lark via WebSocket. It receives messages from Feishu users, enriches them with memory context, and forwards them to Claude Code. Responses flow back through the Feishu IM API.

Commands

npm start              # Run with tsx (development)
npm run build          # Compile TypeScript to dist/
npm run typecheck      # Type-check without emitting
bash scripts/start.sh  # Production launcher (loads lark-cli skills)
npm start -- --dry-run # Validate config and module loading without connecting

Architecture

src/index.ts        – Entry point: wires MCP server, LarkChannel, memory, and buffer together
src/config.ts       – Loads config from ~/.claude/channels/lark/.env (dotenv)
src/channel.ts      – LarkChannel: Feishu WebSocket client, message parsing, memory enrichment pipeline
src/tools.ts        – Registers 14 MCP tools: reply, edit_message, react, download_attachment, save_memory, save_skill, create_job, list_jobs, update_job, delete_job, what_do_you_know, forget_memory, reply_doc_comment, create_doc_comment
src/audit-log.ts    – Append-only audit log for sensitive tool invocations
src/feishu-card.ts  – Card builder: markdown optimization, Schema 2.0 card assembly
src/job-store.ts    – Job CRUD: read/write JSON files, sanitizeJobId, expandScheduleAlias
src/scheduler.ts    – JobScheduler: periodic scan (60s), trigger execution, crash recovery
src/queue.ts        – Per-thread sequential message queue
src/memory/
  file.ts           – MemoryStore: local markdown files under ~/.claude/channels/lark/memories/ (Episodes, tiered Profiles public.md/private.md, Skills)
  buffer.ts         – In-memory ring buffer with auto-flush on inactivity
  distiller.ts      – Builds flush prompts to distill buffer into episodic memory; parseTieredProfile with L1 safety net
src/privacy-rules.ts  – L1 hardcoded regex + keyword rules; L2 user-rules file (privacy-rules.md) read/append
src/enrichment-dedup.ts – EnrichmentDedup: content-hash dedup of memory_context blocks on hot threads (#189); renderEnrichmentParts assembly
src/session-health.ts – SessionHealthMonitor: idle+threshold-gated owner nudge to /compact (#190); reads Stop-hook-written session-stats sidecar

Read the full file on GitHub · 106 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.

2mo ago First seen · 106 lines · 4,085 tokens per session scan A c5dcb0b744e0

Subscribe to this mod's changes

claude-lark-plugin CLAUDE.md is an instructions file published in the GitHub repository IS908/claude-lark-plugin (7 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 4,085 tokens to every session, about $0.0163 per session on Opus 5.5. 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.

bot claude-code-plugin feishu im lark lite-memory

claude-lark-plugin CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-lark-plugin CLAUDE.mdIS908/claude-lark-plugin	Instructions file	7	4mo ago	Apache-2.0	A	4,085	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-lark-plugin: Instructions file for Claude Code