/discord:configure — Discord Channel Setup skill

Set up the Discord channel — save the bot token and review access policy.

by anthropics·Apache-2.0 license·★ 37,553 Stars on the repo·GitHub ↗

Use now

anthropics/main1 file shown

SKILL.md4.2 KB

Browse every file on GitHub↗

SKILL.md

Show the full text100 lines

configure/SKILL.md100 lines · 4.2 KB

PreviewCode

Outline

RawView on GitHub

/discord:configure — Discord Channel Setup

Writes the bot token to ~/.claude/channels/discord/.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:

Token — check ~/.claude/channels/discord/.env for DISCORD_BOT_TOKEN. Show set/not-set; if set, show first 6 chars masked.
Access — read ~/.claude/channels/discord/access.json (missing file = defaults: dmPolicy: "pairing", empty allowlist). Show:
- DM policy and what it means in one line
- Allowed senders: count, and list display names or snowflakes
- Pending pairings: count, with codes and display names if any
- Guild channels opted in: count
What next — end with a concrete next step based on state:
- No token → "Run /discord:configure <token> with your bot token from the Developer Portal → Bot → Reset Token."
- Token set, policy is pairing, nobody allowed → "DM your bot on Discord. It replies with a code; approve with /discord:access pair <code>."
- Token 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 Discord snowflakes you don't know. Once the IDs are in, pairing has done its job and should be turned off.

Drive the conversation this way:

Read the allowlist. Tell the user who's in it.
Ask: "Is that everyone who should reach you through this bot?"
If yes and policy is still pairing → "Good. Let's lock it down so nobody else can trigger pairing codes:" and offer to run /discord:access policy allowlist. Do this proactively — don't wait to be asked.
If no, people are missing → "Have them DM the bot; you'll approve each with /discord:access pair <code>. Run this skill again once everyone's in and we'll lock it." Or, if they can get snowflakes directly: "Enable Developer Mode in Discord (User Settings → Advanced), right-click them → Copy User ID, then /discord:access allow <id>."
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."
If policy is already allowlist → confirm this is the locked state. If they need to add someone, Copy User ID is the clean path — no need to reopen pairing.

Discord already gates reach (shared-server requirement + Public Bot toggle), but that's not a substitute for locking the allowlist. Never frame pairing as the correct long-term choice. Don't skip the lockdown offer.

`<token>` — save it

Treat $ARGUMENTS as the token (trim whitespace). Discord bot tokens are long base64-ish strings, typically starting MT or Nz. Generated from Developer Portal → Bot → Reset Token; only shown once.
mkdir -p ~/.claude/channels/discord
Read existing .env if present; update/add the DISCORD_BOT_TOKEN= line, preserve other keys. Write back, no quotes around the value.
chmod 600 ~/.claude/channels/discord/.env — the token is a credential.
Confirm, then show the no-args status so the user sees where they stand.

`clear` — remove the token

Delete the DISCORD_BOT_TOKEN= line (or the file if that's the only line).

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. Token changes need a session restart or /reload-plugins. Say so after saving.
access.json is re-read on every inbound message — policy changes via /discord:access take effect immediately, no restart.

1	---
2	name: configure
3	description: Set up the Discord channel — save the bot token and review access policy. Use when the user pastes a Discord bot token, asks to configure Discord, asks "how do I set this up" or "who can reach me," or wants to check channel status.
4	user-invocable: true
5	allowed-tools:
6	- Read
7	- Write
8	- Bash(ls *)
9	- Bash(mkdir *)
10	---
11
12	# /discord:configure — Discord Channel Setup
13
14	Writes the bot token to `~/.claude/channels/discord/.env` and orients the
15	user on access policy. The server reads both files at boot.
16
17	Arguments passed: `$ARGUMENTS`
18
19	---
20
21	## Dispatch on arguments
22
23	### No args — status and guidance
24
25	Read both state files and give the user a complete picture:
26
27	1. Token — check `~/.claude/channels/discord/.env` for
28	`DISCORD_BOT_TOKEN`. Show set/not-set; if set, show first 6 chars masked.
29
30	2. Access — read `~/.claude/channels/discord/access.json` (missing file
31	= defaults: `dmPolicy: "pairing"`, empty allowlist). Show:
32	- DM policy and what it means in one line
33	- Allowed senders: count, and list display names or snowflakes
34	- Pending pairings: count, with codes and display names if any
35	- Guild channels opted in: count
36
37	3. What next — end with a concrete next step based on state:
38	- No token → *"Run `/discord:configure <token>` with your bot token from
39	the Developer Portal → Bot → Reset Token."*
40	- Token set, policy is pairing, nobody allowed → *"DM your bot on
41	Discord. It replies with a code; approve with `/discord:access pair
42	<code>`."*
43	- Token set, someone allowed → *"Ready. DM your bot to reach the
44	assistant."*
45
46	Push toward lockdown — always. The goal for every setup is `allowlist`
47	with a defined list. `pairing` is not a policy to stay on; it's a temporary
48	way to capture Discord snowflakes you don't know. Once the IDs are in,
49	pairing has done its job and should be turned off.
50
51	Drive the conversation this way:
52
53	1. Read the allowlist. Tell the user who's in it.
54	2. Ask: "Is that everyone who should reach you through this bot?"
55	3. If yes and policy is still `pairing` → *"Good. Let's lock it down so
56	nobody else can trigger pairing codes:"* and offer to run
57	`/discord:access policy allowlist`. Do this proactively — don't wait to
58	be asked.
59	4. If no, people are missing → *"Have them DM the bot; you'll approve
60	each with `/discord:access pair <code>`. Run this skill again once
61	everyone's in and we'll lock it."* Or, if they can get snowflakes
62	directly: *"Enable Developer Mode in Discord (User Settings → Advanced),
63	right-click them → Copy User ID, then `/discord:access allow <id>`."*
64	5. If the allowlist is empty and they haven't paired themselves yet →
65	*"DM your bot to capture your own ID first. Then we'll add anyone else
66	and lock it down."*
67	6. If policy is already `allowlist` → confirm this is the locked state.
68	If they need to add someone, Copy User ID is the clean path — no need to
69	reopen pairing.
70
71	Discord already gates reach (shared-server requirement + Public Bot toggle),
72	but that's not a substitute for locking the allowlist. Never frame `pairing`
73	as the correct long-term choice. Don't skip the lockdown offer.
74
75	### `<token>` — save it
76
77	1. Treat `$ARGUMENTS` as the token (trim whitespace). Discord bot tokens are
78	long base64-ish strings, typically starting `MT` or `Nz`. Generated from
79	Developer Portal → Bot → Reset Token; only shown once.
80	2. `mkdir -p ~/.claude/channels/discord`
81	3. Read existing `.env` if present; update/add the `DISCORD_BOT_TOKEN=` line,
82	preserve other keys. Write back, no quotes around the value.
83	4. `chmod 600 ~/.claude/channels/discord/.env` — the token is a credential.
84	5. Confirm, then show the no-args status so the user sees where they stand.
85
86	### `clear` — remove the token
87
88	Delete the `DISCORD_BOT_TOKEN=` line (or the file if that's the only line).
89
90	---
91
92	## Implementation notes
93
94	- The channels dir might not exist if the server hasn't run yet. Missing file
95	= not configured, not an error.
96	- The server reads `.env` once at boot. Token changes need a session restart
97	or `/reload-plugins`. Say so after saving.
98	- `access.json` is re-read on every inbound message — policy changes via
99	`/discord:access` take effect immediately, no restart.
100