slack-webhook

slack-webhook is a skill for Claude Code, Codex from tomeraitz/claude-slack-bridge. It costs 59 tokens per session (800 once invoked), scanned A, original, MIT.

A script for sending Slack messages as Claude through a webhook, a configured URL that accepts messages. Slack is a team chat service.

In plain words
What is it for?
Use it to send progress updates, completed-task notices, alerts, mentions, or messages to a configured Slack channel.
Why use it?
It makes messages appear as coming from Claude and can notify the user, unlike messages posted through a connection acting as the user.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to send progress updates, completed-task notices, alerts, mentions, or messages to a configured Slack channel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomeraitz/claude-slack-bridge/slack-webhook
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 tomeraitz/claude-slack-bridge --skill slack-webhook
Clone the repo
git clone --depth 1 https://github.com/tomeraitz/claude-slack-bridge

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.

agentmods badge for slack-webhook

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomeraitz/claude-slack-bridge/slack-webhook.svg)](https://agentmods.dev/skills/tomeraitz/claude-slack-bridge/slack-webhook)
Your own site
<a href="https://agentmods.dev/skills/tomeraitz/claude-slack-bridge/slack-webhook"><img src="https://agentmods.dev/badge/skills/tomeraitz/claude-slack-bridge/slack-webhook.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 800 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00059 $0.00800
Opus 5 $0.00030 $0.00400
Sonnet 5 $0.00012 $0.00160
Haiku 4.5 $0.00006 $0.00080

Measured 8d ago against content hash f2e4a9a54f94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

slack-webhook 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (send.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/slack-webhook/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Send Slack messages as Claude

One command, one message, straight into the user's Slack.

python skills/slack-webhook/send.py "Migration finished — 412 rows moved, no errors."

Use this, not the Slack connector

The built-in Slack tools authenticate as the user, so anything they post looks like the user talking to themselves — and Slack doesn't notify anyone about their own message. This script posts through a webhook owned by the Claude app, so it arrives as Claude and can @-mention the user for a real notification.

Never reach the user through the Slack connector. If this script fails, say so rather than quietly falling back to it.

Options

# ping the user so their phone lights up
send.py --mention U0123ABCDEF "Need a decision before I continue."

# a different channel (each webhook is bound to one)
send.py --to design "New mockups are in the PR."

# short one-liners, Slack's own syntax, raw emoji
send.py --plain ":white_check_mark: build green"

# what's available
send.py --list
Flag Does
--mention U… @-mentions that member — the thing that actually pushes a notification
--to NAME picks a configured webhook; each one posts to a fixed channel
--plain sends Slack mrkdwn instead of a markdown block
--list prints the configured webhook names

By default the message is a markdown block: headings, lists, tables, links, and fenced code all render. Use --plain for one-liners and :emoji:.

What it can't do

Read anything. A webhook is write-only, so there is no way to receive the user's reply here. If you need an answer:

  • ask the question, then stop and wait for the user in this chat, or
  • use the slack-as-claude skill (needs a bot token), which polls the thread.

Don't claim you'll "wait for their Slack reply" — you won't see it.

When to send

  1. Finishing long work, so the user doesn't have to keep checking.
  2. Blocking on a decision — send the question, then wait here.
  3. Failing in a way they need to know about now.

Read the full file on GitHub · 90 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 90 lines · 59 tokens per session scan A f2e4a9a54f94

Subscribe to this mod's changes

slack-webhook is a skill published in the GitHub repository tomeraitz/claude-slack-bridge (33 stars, last pushed 18d ago), licensed MIT. It adds 59 tokens to every session and 800 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 2026-08-30.