configure skill
✓ VerifiedChecks iMessage channel setup, verifies Full Disk Access, and reviews access policies for incoming messages.
- GitHub stars
- 171
- Files
- 1
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- 2
What does the configure skill do?
configure checks iMessage channel setup, verifies Full Disk Access, and reviews access policies for incoming messages.
Summary generated from the skill's SKILL.md.
About the configure skill
Troubleshooting iMessage connectivity and managing communication permissions is what this skill enables for developers using Claude Code. It functions by inspecting the local system to ensure the assistant can actually read the iMessage database located at ~/Library/Messages/chat.db. An agent should load this tool when a user asks how to set up the channel, questions who can reach them, or reports that incoming texts are not appearing.
The tool performs specific diagnostic checks, such as using Bash to verify if Full Disk Access is granted to the terminal or IDE. It also reviews the access.json file to report on the current direct message policy, the number of allowed senders, and any pending pairings. By providing clear instructions for system settings and suggesting specific commands like /imessage:access allow, it helps users move from a broken state to a functional allowlist configuration without needing to manage manual tokens.
What an agent can do with it
- 1Diagnose message delivery failuresAsk the assistant to find out why incoming iMessages are not reaching the interface.
- 2Verify system permissionsCheck if the terminal has the necessary Full Disk Access to read the chat database.
- 3Audit communication access policiesReview the current allowlist and see which specific handles are permitted to send messages.
- 4Correct dangerous pairing settingsIdentify if the pairing policy is active and suggest switching to a safer allowlist.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the configure skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the configure skill in Claude Code
~/.claude/skills/configure/SKILL.md
$ npx degit thevibeworks/claude-code-docs/content/github/claude-plugins-official/external_plugins/imessage/skills/configure ~/.claude/skills/configureInstall the configure skill in Claude Code (project)
.claude/skills/configure/SKILL.md
$ npx degit thevibeworks/claude-code-docs/content/github/claude-plugins-official/external_plugins/imessage/skills/configure .claude/skills/configureInstall the configure skill in Codex
~/.agents/skills/configure/SKILL.md
$ npx degit thevibeworks/claude-code-docs/content/github/claude-plugins-official/external_plugins/imessage/skills/configure ~/.agents/skills/configureInstall the configure skill in Gemini CLI
~/.gemini/skills/configure/SKILL.md
$ npx degit thevibeworks/claude-code-docs/content/github/claude-plugins-official/external_plugins/imessage/skills/configure ~/.gemini/skills/configureInstall the configure skill in Claude.ai
npx degit thevibeworks/claude-code-docs/content/github/claude-plugins-official/external_plugins/imessage/skills/configure configure && zip -r configure.zip configure # claude.ai → Customize → Skills → + → Create skill → Upload a skill → configure.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablethevibeworks/claude-code-docs/content/github/claude-plugins-official/external_plugins/imessage/skills/configure is public and reachablegithub.com/thevibeworks/claude-code-docs/tree/HEAD/content/g ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/thevibeworks/claude-code-docs/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/thevibeworks/claude-code-docs/blob/HEAD/content/g ↗Pass
- Pre-approved tools are scopedPre-approved: Read, Bash(ls *)github.com/thevibeworks/claude-code-docs/blob/HEAD/content/g ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 83 linesgithub.com/thevibeworks/claude-code-docs/blob/HEAD/content/g ↗Pass
SKILL.md
View on GitHub/imessage:configure — iMessage Channel Setup
There's no token to save — iMessage reads ~/Library/Messages/chat.db
directly. This skill checks whether that works and orients the user on
access policy.
Arguments passed: $ARGUMENTS (unused — this skill only shows status)
Status and guidance
Read state and give the user a complete picture:
-
Full Disk Access — run
ls ~/Library/Messages/chat.db. If it fails with "Operation not permitted", FDA isn't granted. Say: "Grant Full Disk Access to your terminal (or IDE if that's where Claude Code runs): System Settings → Privacy & Security → Full Disk Access. The server can't read chat.db without it." -
Access — read
~/.claude/channels/imessage/access.json(missing file = defaults:dmPolicy: "allowlist", empty allowlist). Show:- DM policy and what it means in one line
- Allowed senders: count, and list the handles
- Pending pairings: count, with codes if any (only if policy is
pairing)
-
What next — end with a concrete next step based on state:
- FDA not granted → the FDA instructions above
- FDA granted, policy is allowlist → "Text yourself from any device
signed into your Apple ID — self-chat always bypasses the gate. To let
someone else through:
/imessage:access allow +15551234567." - FDA granted, someone allowed → "Ready. Self-chat works; {N} other sender(s) allowed."
Build the allowlist — don't pair
iMessage reads your personal chat.db. You already know the phone
numbers and emails of people you'd allow — there's no ID-capture problem to
solve. Pairing has no upside here and a clear downside: every contact who
texts this Mac gets an unsolicited auto-reply.
Drive the conversation this way:
- Read the allowlist. Tell the user who's in it (self-chat always works regardless).
- Ask: "Besides yourself, who should be able to text you through this?"
- "Nobody, just me" → done. The default
allowlistwith an empty list is correct. Self-chat bypasses the gate. - "My partner / a friend / a couple people" → ask for each handle
(phone like
+15551234567or email likethem@icloud.com) and offer to run/imessage:access allow <handle>for each. Stay onallowlist. - Current policy is
pairing→ flag it immediately: "Your policy ispairing, which auto-replies a code to every contact who texts this Mac. Switch back toallowlist?" and offer/imessage:access policy allowlist. Don't wait to be asked. - User asks for
pairing→ push back. Explain the auto-reply-to- everyone consequence. If they insist and confirm a dedicated line with few contacts, fine — but treat it as a one-off, not a recommendation.
Handles are +15551234567 or someone@icloud.com. disabled drops
everything except self-chat.
Implementation notes
- No
.envfile for this channel. No token. The only OS-level setup is FDA plus the one-time Automation prompt when the server first sends (which can't be checked from here). access.jsonis re-read on every inbound message — policy changes via/imessage:accesstake effect immediately, no restart.
Files in this skill
1configure skill questions
How do I install the configure skill in Claude Code?
Run npx degit thevibeworks/claude-code-docs/content/github/claude-plugins-official/external_plugins/imessage/skills/configure ~/.claude/skills/configure. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the configure skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How do I fix 'Operation not permitted' when setting up iMessage?
You need to grant Full Disk Access to your terminal or IDE via System Settings → Privacy & Security → Full Disk Access.
How can I allow someone else to text me through this assistant?
You can add specific handles using the command /imessage:access allow +15551234567 or an email address.
What is the difference between allowlist and pairing policies?
The allowlist policy only permits specific contacts, while the pairing policy sends an unsolicited auto-reply code to every contact who texts the Mac.