summarize-channel

summarize-channel is a command for Claude Code from anthropics/knowledge-work-plugins. It costs 9 tokens per session (233 once invoked), scanned A, original, Apache-2.0.

A command that summarizes recent activity in a Slack channel, including threaded replies. It organizes the result around topics, decisions, action items, announcements, and open discussions.

In plain words
What is it for?
Use it to catch up on a channel, extract decisions and follow-ups, review announcements, and report when a channel has little recent activity.
Why use it?
It saves developers from reading every recent message and reduces the chance of missing important information buried in reply threads.

Command for Claude Code ✓ vendor

Written for Claude Code: $ARGUMENTS substitution.

Part of the slack-by-salesforce plugin — 2 skills, 5 commands shipped together

Good fit Use it to catch up on a channel, extract decisions and follow-ups, review announcements, and report when a channel has little recent activity.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/anthropics/knowledge-work-plugins/summarize-channel
About the project

Knowledge Work Plugins is an open-source collection of Claude extensions organized around roles such as productivity, sales, and customer support. Each plugin combines role-specific guidance, connectors, commands, and sub-agents so knowledge workers can use Claude with their team’s tools and processes. The catalogue entries are examples of, or workflows from, this plugin collection.

anthropics/knowledge-work-plugins · 23,911 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/anthropics/knowledge-work-plugins

Made for: Claude Code.

Or install slack-by-salesforce, the plugin that ships this one along with the rest of its 2 skills, 5 commands.

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.

agentmods badge for summarize-channel

README.md
[![agentmods](https://agentmods.dev/badge/commands/anthropics/knowledge-work-plugins/summarize-channel.svg)](https://agentmods.dev/commands/anthropics/knowledge-work-plugins/summarize-channel)
Your own site
<a href="https://agentmods.dev/commands/anthropics/knowledge-work-plugins/summarize-channel"><img src="https://agentmods.dev/badge/commands/anthropics/knowledge-work-plugins/summarize-channel.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 233 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00009 $0.00233
Opus 5 $0.00005 $0.00117
Sonnet 5 $0.00002 $0.00047
Haiku 4.5 $0.00001 $0.00023

Measured 4d ago against content hash 1719cc1abd99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

summarize-channel 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

partner-built/slack/commands/summarize-channel.md · 17 lines

What it actually says

Given the channel name provided in $ARGUMENTS (strip any leading #):

  1. Use the slack_search_channels tool to find the channel ID for the provided channel name. Strip any leading # from the argument before searching.
  2. Use the slack_read_channel tool to read recent messages from the channel (default limit of 100 messages).
  3. For any messages that have threads with replies, use slack_read_thread to read the thread contents so the summary captures threaded discussions.
  4. Produce a concise summary organized by topic or theme. The summary should include:
    • An overview of the main topics discussed
    • Key decisions or action items mentioned
    • Notable announcements or updates
    • Active threads and their conclusions (if any)
  5. Keep the summary scannable — use short bullet points grouped by topic. Mention who said what when it's relevant (e.g., decisions, action items).
  6. If the channel has very little recent activity, say so and note the last time a message was posted.
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.

  1. 4d ago First seen · 17 lines · 9 tokens per session scan A 1719cc1abd99

Subscribe to this mod's changes

summarize-channel is a command published in the GitHub repository anthropics/knowledge-work-plugins (23,911 stars, last pushed 2d ago), licensed Apache-2.0. It adds 9 tokens to every session and 233 once invoked, about $0.0000 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 2026-09-03.