What is agents-to-im?

A tool for managing a bridge between Claude Code or Codex and Feishu/Lark, a workplace messaging platform.

Use it for setup, health checks, logs, upgrades, and service control of the Feishu/Lark bridge.

It helps configure, start, stop, inspect, upgrade, and diagnose the bridge daemon that connects the coding agent to Feishu/Lark.

agents-to-im — Skill for Claude Code and Codex by francize

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 francize/agents-to-im --skill agents-to-im

Clone the repo

git clone --depth 1 https://github.com/francize/agents-to-im

Made for: Claude Code, Codex.

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/skills/francize/agents-to-im/agents-to-im/github.svg)](https://agentmods.dev/skills/francize/agents-to-im/agents-to-im)

Your own site

<a href="https://agentmods.dev/skills/francize/agents-to-im/agents-to-im"><img src="https://agentmods.dev/badge/skills/francize/agents-to-im/agents-to-im/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/skills/francize/agents-to-im/agents-to-im"><img src="https://agentmods.dev/badge/skills/francize/agents-to-im/agents-to-im.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 711 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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.00711
Opus 5	$0.00030	$0.00356
Sonnet 5	$0.00012	$0.00142
Haiku 4.5	$0.00006	$0.00071

Measured 11d ago against content hash a676e79a574b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agents-to-im 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 11d 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.

SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents to IM Skill

You are managing the Feishu/Lark bridge daemon. User data is stored at ~/.agents-to-im/.

The skill directory is ~/.claude/skills/agents-to-im. If that path does not exist, find SKILL.md via glob and derive the root directory from it.

Commands

Map $ARGUMENTS to one of:

onboard
setup
start
stop
status
logs
doctor
upgrade

If no configuration exists at ~/.agents-to-im/config.env, show config.env.example and explain the required Feishu fields. Do not try to start the daemon without config.

CLI usage

Prefer the globally installed npm CLI:

install once: npm install -g agents-to-im@beta
agents-to-im onboard
agents-to-im start
agents-to-im restart
agents-to-im status
agents-to-im doctor
agents-to-im upgrade
agents-to-im logs 100

Use source checkout commands only for development/debugging.

Setup

This project no longer has a multi-platform setup wizard. Setup means:

Show config.env.example.
Explain the required fields:
- CTI_FEISHU_APP_ID
- CTI_FEISHU_APP_SECRET
- CTI_DEFAULT_WORKDIR
Explain optional fields:
- CTI_FEISHU_DOMAIN
- CTI_FEISHU_ALLOWED_USERS
- external CODEX_HOME override if the user stores Codex config outside ~/.codex
Point the user to references/setup-guides.md for the one-shot Feishu scopes import JSON.
Remind the user to enable Feishu long connection events:
- im.message.receive_v1
- card.action.trigger
Remind the user that private chat only accepts /new:claude and /new:codex, and real conversation happens in the auto-created group.

Runtime behavior

Runtime is selected per session.
/new:claude creates a Claude session.
/new:codex creates a Codex session.
/reset keeps the current group's runtime.

Execution

Use:

agents-to-im onboard
bash "SKILL_DIR/scripts/daemon.sh" start
bash "SKILL_DIR/scripts/daemon.sh" stop
bash "SKILL_DIR/scripts/daemon.sh" status
bash "SKILL_DIR/scripts/daemon.sh" logs 50
bash "SKILL_DIR/scripts/doctor.sh"

Read the full file on GitHub · 94 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.

11d ago First seen · 94 lines · 61 tokens per session scan A a676e79a574b

Subscribe to this mod's changes

agents-to-im is a skill published in the GitHub repository francize/agents-to-im (118 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 711 once invoked, about $0.0003 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.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

agents-to-im