recipe-skills: Command for Claude Code

.claude/commands/slack-recipes.md

slack-recipes is a command for Claude Code from workato-devs/recipe-skills. It costs 0 tokens per session (909 once invoked), scanned A, original, MIT.

A guide for building Workato automations that use Slack, either through interactive bots or Slack's API. Workato is a service for connecting apps and automating workflows.

In plain words
What is it for?
Use it to create Slack slash commands, interactive bot workflows, channel or direct messages, user lookups, channel creation, and callable automations.
Why use it?
It helps choose the right Slack connection and structure recipes for messages, commands, buttons, dialogs, and user or channel management.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is workato-devs/recipe-skills's own configuration. It tells Claude Code how to work on recipe-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything recipe-skills configures →

Part of the recipe-skills plugin — 8 skills, 7 commands shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to workato-devs/recipe-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/workato-devs/recipe-skills/main/.claude/commands/slack-recipes.md
Clone the repo
git clone --depth 1 https://github.com/workato-devs/recipe-skills

Made for: Claude Code.

Or install recipe-skills, the plugin that ships this one along with the rest of its 8 skills, 7 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 slack-recipes

README.md
[![agentmods](https://agentmods.dev/badge/commands/workato-devs/recipe-skills/slack-recipes/github.svg)](https://agentmods.dev/commands/workato-devs/recipe-skills/slack-recipes)
Your own site
<a href="https://agentmods.dev/commands/workato-devs/recipe-skills/slack-recipes"><img src="https://agentmods.dev/badge/commands/workato-devs/recipe-skills/slack-recipes/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for slack-recipes

Your own site · 80×15
<a href="https://agentmods.dev/commands/workato-devs/recipe-skills/slack-recipes"><img src="https://agentmods.dev/badge/commands/workato-devs/recipe-skills/slack-recipes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 909 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 $0.00000 $0.00909
Opus 5 $0.00000 $0.00454
Sonnet 5 $0.00000 $0.00182
Haiku 4.5 $0.00000 $0.00091

Measured 8d ago against content hash 6f3d88f2e782, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

slack-recipes 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.

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.

.claude/commands/slack-recipes.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slack Recipes Skill

DEPENDENCY: Run /workato-recipes first if not already loaded. This skill requires the base Workato knowledge for triggers, control flow, datapills, and recipe structure.

You are now equipped with Slack-specific knowledge for writing Workato recipes. This skill covers two Slack connectors:

Connector Provider Use Case
Workbot for Slack slack_bot Interactive bots, slash commands, dialogs, buttons
Slack (native) slack Programmatic actions via API-triggered recipes

Capabilities

With this skill loaded, you can:

  • Create recipes with Workbot command triggers and slash commands
  • Create recipes that post messages to channels and DMs
  • Create recipes with interactive dialogs/modals
  • Create recipes with button interactions
  • Create recipes that chain to other Workbot recipes
  • Create callable recipes using native Slack actions
  • Look up users by email, create channels, manage membership

Choosing a Connector

Use Workbot (slack_bot) when the trigger is a user interaction (slash command, button click).

Use Native Slack (slack) when the trigger is an API call, scheduler, or another system.

Slack-Specific Knowledge

Provider

Always use slack_bot (Workbot for Slack), not slack:

"provider": "slack_bot"

Datapill Paths (CRITICAL)

Slack does NOT use the ["body"] wrapper for trigger context:

// CORRECT for Slack trigger context
"path": ["context", "user"]
"path": ["context", "channel"]
"path": ["context", "trigger_id"]
"path": ["parameters", "project_name"]

// For adhoc HTTP responses, body IS used
"path": ["body", "channel", "id"]

Dialog Parameters

Parameters are defined as a JSON string with control types:

  • text - Single-line input (150 char max)
  • text-area - Multi-line input (3000 char max)
  • select - Dropdown with pick_list options

Sending DMs

Target the triggering user's DM:

"channel": "=_dp('{...path:[\"context\",\"user\"]}').gsub('\"','')"

Read the full file on GitHub · 112 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.

  1. 8d ago First seen · 112 lines · 0 tokens per session scan A 6f3d88f2e782

Subscribe to this mod's changes

slack-recipes is a command published in the GitHub repository workato-devs/recipe-skills (18 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 909 tokens. 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.