What is slack-reader?

A Slack helper that lets an agent read workspace conversations and publish messages, replies, or reactions. Slack is a team messaging service, and this helper uses a Slack user token to access it.

For finding messages, reading channel or direct-message history, expanding threads, summarizing activity, and sending or managing messages and reactions.

It removes the need to search channels, open threads, and post updates manually when working with Slack information.

slack-reader — Skill for Claude Code and Codex by EgumaYuto

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.

Any agent

npx skills add EgumaYuto/slack-mcp --skill slack-reader

Clone the repo

git clone --depth 1 https://github.com/EgumaYuto/slack-mcp

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/egumayuto/slack-mcp/slack-reader.svg)](https://agentmods.dev/skills/egumayuto/slack-mcp/slack-reader)

Your own site

<a href="https://agentmods.dev/skills/egumayuto/slack-mcp/slack-reader"><img src="https://agentmods.dev/badge/skills/egumayuto/slack-mcp/slack-reader.svg" alt="Measured on agentmods" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 974 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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.00974
Opus 5	$0.00032	$0.00487
Sonnet 5	$0.00013	$0.00195
Haiku 4.5	$0.00006	$0.00097

Measured 6d ago against content hash 7a92b0d12a03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

slack-reader 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 6d 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.

skill/slack-reader/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slack

Access to Slack through the slack-mcp MCP server. Requires the server to be registered (tools named slack_*) with a Slack user token (xoxp-).

Available tools

Reading

slack_whoami — verify the token / identify the workspace.
slack_list_channels — get channel & DM ids. types = comma list of public_channel,private_channel,im,mpim.
slack_get_history — read recent messages of a channel/DM by id.
slack_get_activity — everything in a time window, including replies to threads started before it. Use this for "what happened this week" style summaries.
slack_get_thread — expand a thread (needs channel id + parent thread_ts).
slack_search — workspace full-text search with operators.
slack_list_users — resolve members.

Writing

slack_post_message — post to a channel/DM. Pass thread_ts to reply in a thread.
slack_add_reaction — add an emoji reaction (name without colons).
slack_update_message — replace the body of a message the user authored.
slack_delete_message — delete a message the user authored. Irreversible.

How to work

Resolve names to ids first. Users refer to channels by name ("#general") or people by handle, but history/thread tools need ids. Use slack_list_channels (or slack_search with in:#name) to get the id.
Read history with slack_get_history. Default limit is small (30) — raise limit or paginate via the returned next_cursor when the user wants more history. For a time range ("this week", "since Monday") use slack_get_activity instead: slack_get_history returns only top-level messages, so ongoing thread discussions are silently missed.
Threads: messages with reply_count are thread parents. To read the full discussion, call slack_get_thread with that message's ts as thread_ts.
Search with slack_search. Prefer Slack operators to narrow results:
- in:#channel / in:@dm
- from:@user
- after:2024-01-01 / before:2024-12-31 / on:2024-06-01
- quote phrases: "exact phrase" Search returns permalink — include it when citing a message.
Posting: show the user the exact text and the target channel, and get their confirmation, before calling slack_post_message — the message goes out under their own name and cannot be un-sent (only deleted after the fact). To reply in a thread rather than the channel, pass the parent's ts as thread_ts.
Editing/deleting: only the token's own messages can be changed. Deletion is permanent — always confirm the specific message with the user first.

Read the full file on GitHub · 71 lines

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.

6d ago First seen · 71 lines · 64 tokens per session scan A 7a92b0d12a03

Subscribe to this mod's changes

slack-reader is a skill published in the GitHub repository EgumaYuto/slack-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 974 once invoked, about $0.0003 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 2026-08-31.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

mochi-remind

Handle due reminders — notify the user with natural language and mark them done.

kirodotdev/KiroCrew · 20 tokens