Skip to main content
skill CX Codex

comms-summarize — Claude Code skill for message summaries

The comms-summarize Claude Code skill summarizes unread messages from an inbox, channel, or thread. It flags items that need action and separates them from FYI and stale messages.

MIT ★ 26 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add wrg32786/aigent-os --skill comms-summarize -a claude-code
Open on GitHub

What comms-summarize does

The skill reads an inbox file, channel log, thread, or directory of message files, then sorts messages into action required, FYI, and stale. Each entry includes the sender and topic; action items also state what response or decision is needed.

It is read-only and does not draft or send replies. It reads files with Read and Glob and searches with Grep. The source is a file path, directory, or channel; if a source file does not exist, the skill reports that and stops.

What it helps with

  • sort unread inbox messages by whether they need action
  • surface decisions needed in a channel log
  • separate current information from stale threads

Example prompts for the agent

  • Summarize unread messages in inbox.md.
  • Check the #release channel log and list items that need a decision.
  • Summarize the conversation files in messages/.

How to install comms-summarize

1Skills CLI (Vercel)

npx skills add wrg32786/aigent-os --skill comms-summarize -a claude-code

2Manually: put the files in place

~/.claude/skills/comms-summarize/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/comms-summarize/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about comms-summarize

How do I install comms-summarize in Claude Code?

Run npx skills add wrg32786/aigent-os --skill comms-summarize -a claude-code. The skill file is at ~/.claude/skills/comms-summarize/SKILL.md.

What does comms-summarize do?

It reads a message source and groups items into action required, FYI, and stale. It does not write or send replies.

What message sources can comms-summarize read?

You can provide a file path, a directory of message files, or a channel. If no source is given, the skill asks for one.

Source text

SKILL.md · MIT
---
name: comms-summarize
agent: echo
description: "Summarize unread inbox, channel, or thread messages with sender, topic, action, and urgency. Use when checking inboxes or polling comms. Read-only."
allowed-tools: Read, Grep, Glob
user-invocable: true
triggers:
  - summarize comms
  - comms summary
  - what's unread
  - check inbox
  - poll messages
  - unread messages
  - summarize channel
  - what came in
---

# Comms Summarize

You are Echo performing a comms polling pass. Read-only without exception.

## What this skill does

Read a comms source (inbox file, channel log, message thread, or directory of message files) and return a structured summary of unread or recent messages. Identify what needs action, what is informational, and what can be ignored. Do not reply, draft, or write anything.

## Protocol

1. **Identify the source.** The user will specify a file path, directory, or channel. If not specified, ask once.
2. **Read the source.** Use Read or Glob to load the relevant files.
3. **Classify each message/thread:**
   - ACTION REQUIRED — needs a response or decision
   - FYI — informational, no response needed
   - STALE — old thread, context lost or resolved
4. **Return the summary.**

## Return format

```
## Comms Summary — <source> — <date>

### Action Required (N)
- [SENDER] <subject/topic> — <one-line context> — **Action:** <what's needed>

### FYI (N)
- [SENDER] <subject/topic> — <one-line context>

### Stale / Skip (N)
- [SENDER] <subject/topic> — <reason to skip>

### Stats
- Total messages scanned: N
- Oldest unread: <date>
```

## Constraints

- No Write, Edit, Bash, or Agent tool calls.
- No drafting replies. Surface only.
- If the source file doesn't exist, say so and stop.
- Run all Read calls in parallel where possible.

© wrg32786 · MIT · wrg32786/aigent-os

Similar skills

All skills for Notes, tasks and projects →

From the same set58

The whole set →
critique-plan The critique-plan Claude Code skill challenges strategic plans, architectural decisions, and proposals before approval. It surfaces counterarguments, hidden assumptions, and alternatives. CX Codex +1 ★ 26repo stars context-hygiene This Claude Code skill archives old session log entries and trims active priorities. Run /context-hygiene to clean the context files. CX Codex +1 ★ 26repo stars context-capsule The context-capsule Claude Code skill saves the current project state in a capsule for later work. Run it to checkpoint before risky changes, mark a completed milestone, or hand work to another session. CX Codex +1 ★ 26repo stars compact-note The compact-note Claude Code skill condenses long notes and logs while keeping the reasoning behind decisions. It runs on requests to shorten a note, log, or memory. CX Codex +1 ★ 26repo stars cognitive-update The cognitive-update Claude Code skill updates goals, beliefs, self-model fields, and procedures from explicit evidence. It activates for cognitive or runtime state changes. CX Codex +1 ★ 26repo stars codex-adapter The codex-adapter Claude Code skill hands one bounded, mechanical change to OpenAI Codex CLI. It activates on an explicit request to delegate a rename, config edit, or scripted replacement. CX Codex +1 ★ 26repo stars close This Claude Code skill saves session outcomes to durable memory and prepares a resume point. Run /close to wrap up work and update notes in vault/. CX Codex +1 ★ 26repo stars capsule-compact The capsule-compact Claude Code skill condenses long chains of context capsules. Run it on request or when a chain has grown too long. CX Codex +1 ★ 26repo stars

Project sponsors

Companies that keep this analytics open