/feishu:configure — Feishu Channel Setup

Writes the app credentials to ~/.claude/channels/feishu/.env and orients the user on access policy. The server reads both files at boot.

Arguments passed: $ARGUMENTS

Dispatch on arguments

No args — status and guidance

Read both state files and give the user a complete picture:

1. Credentials — check ~/.claude/channels/feishu/.env for

FEISHUAPPID and FEISHUAPPSECRET. Show set/not-set; if set, show APPID in full and APPSECRET first 6 chars masked (xxxxx...).

1. Access — read ~/.claude/channels/feishu/access.json (missing file

= defaults: dmPolicy: "pairing", empty allowlist). Show: - DM policy and what it means in one line - Allowed senders: count, and list open_ids - Pending pairings: count, with codes and sender IDs if any

1. What next — end with a concrete next step based on state:

- No credentials → "Run /feishu:configure <appid> <appsecret> with the credentials from Feishu Open Platform." - Credentials set, policy is pairing, nobody allowed → "DM your bot on Feishu. It replies with a code; approve with /feishu:access pair <code>." - Credentials set, someone allowed → "Ready. DM your bot to reach the assistant."

Push toward lockdown — always. The goal for every setup is allowlist with a defined list. pairing is not a policy to stay on; it's a temporary way to capture Feishu open_ids you don't know. Once the IDs are in, pairing has done its job and should be turned off.

Drive the conversation this way:

1. Read the allowlist. Tell the user who's in it.
2. Ask: "Is that everyone who should reach you through this bot?"
3. If yes and policy is still pairing → *"Good. Let's lock it down so

nobody else can trigger pairing codes:"* and offer to run /feishu:access policy allowlist. Do this proactively — don't wait to be asked.

1. If no, people are missing → *"Have them DM the bot; you'll approve

each with /feishu:access pair <code>. Run this skill again once everyone's in and we'll lock it."*

1. If the allowlist is empty and they haven't paired themselves yet →

"DM your bot to capture your own ID first. Then we'll add anyone else and lock it down."

1. If policy is already allowlist → confirm this is the locked state.

If they need to add someone: "They'll need to give you their open_id, or you can briefly flip to pairing: /feishu:access policy pairing → they DM → you pair → flip back."

Never frame pairing as the correct long-term choice. Don't skip the lockdown offer.

<appid> <appsecret> — save credentials

1. Parse $ARGUMENTS — expect two space-separated values: app_id and

appsecret. Feishu appid looks like cli_xxx.

1. mkdir -p ~/.claude/channels/feishu
2. Read existing .env if present; update/add the FEISHUAPPID= and

FEISHUAPPSECRET= lines, preserve other keys. Write back, no quotes around the values.

1. Confirm, then show the no-args status so the user sees where they stand.

clear — remove credentials

Delete the FEISHUAPPID= and FEISHUAPPSECRET= lines (or the file if those are the only lines).

Feishu app setup guide

If the user hasn't created a Feishu app yet, guide them:

1. Go to Feishu Open Platform → Create App

→ Enterprise Self-Built App

1. In app settings, enable Bot capability
2. Add required permissions (scopes):

- im:message — send and receive messages - im:message:sendasbot — send as bot - im:resource — upload images and files - im:message.reactions:write_only — add reactions (optional)

1. In Events & Callbacks → Event Configuration:

- Select "Use persistent connection to receive events" (长连接) - Subscribe to event: im.message.receive_v1

1. Publish the app version and wait for admin approval
2. Copy App ID and App Secret from the app's Credentials & Basic Info page

Implementation notes

• The channels dir might not exist if the server hasn't run yet. Missing file

= not configured, not an error.

• The server reads .env once at boot. Credential changes need a session

restart or /reload-plugins. Say so after saving.

• access.json is re-read on every inbound message — policy changes via

/feishu:access take effect immediately, no restart.