mochi-slack

mochi-slack is a skill for Claude Code, Codex from kirodotdev/KiroCrew. It costs 28 tokens per session (1,096 once invoked), scanned A, original, Apache-2.0.

A set of instructions for reading Slack activity, including unread mentions, channel updates, monitored topics and discussion threads. It works with whichever Slack tools are available.

In plain words
What is it for?
Finding mentions, summarizing channels or threads, monitoring topics and resolving Slack users when the available tools support those tasks.
Why use it?
Important messages can be spread across many channels and long threads. It helps gather the relevant conversation without assuming a particular Slack connection.

Skill for Claude CodeCodex

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

Good fit Finding mentions, summarizing channels or threads, monitoring topics and resolving Slack users when the available tools support those tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kirodotdev/kirocrew/mochi-slack
About the project

Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.

kirodotdev/KiroCrew · 3,687 stars · on GitHub · kiro.dev

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 kirodotdev/KiroCrew --skill mochi-slack
Clone the repo
git clone --depth 1 https://github.com/kirodotdev/KiroCrew

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 mochi-slack

README.md
[![agentmods](https://agentmods.dev/badge/skills/kirodotdev/kirocrew/mochi-slack.svg)](https://agentmods.dev/skills/kirodotdev/kirocrew/mochi-slack)
Your own site
<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/mochi-slack"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/mochi-slack.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,096 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 $0.00028 $0.01096
Opus 5 $0.00014 $0.00548
Sonnet 5 $0.00006 $0.00219
Haiku 4.5 $0.00003 $0.00110

Measured 8d ago against content hash bdb636308d07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mochi-slack 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.

src/kiro_crew/apps/builtins/mochi/agents/skills/mochi-slack/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@mochi-slack — Slack Awareness

You help the user READ Slack — unread mentions, channel summaries, topic monitoring, thread summaries.

This skill does not assume a particular Slack MCP server

There is no single standard Slack MCP server, and the user may have any of them — public, self-hosted, or one their company provides. So this skill describes the CAPABILITIES each task needs and leaves the tool names to you.

Discover before assuming. Look at the Slack tools you actually have and map them onto the capabilities below. Where a capability is missing, say so plainly instead of guessing at a tool name — a wrong call wastes a turn and confuses the user.

Capabilities the tasks below need:

Capability What you are looking for
List channels channels the user is in, ideally with unread / mention counts
Read a channel recent messages in one channel
Read a thread all replies under one parent message
Search message search, ideally with in: / from: / has: style filters
Resolve a user a user id or handle → display name

Names vary. One common server spells these list_my_channels, get_messages, get_thread, search, lookup_user — treat that as a hint, not a contract.

If you have no Slack tools at all

Do NOT try to install one. Which Slack server to use, and whether to connect a workspace at all, is the user's decision — and on a work machine it may not be theirs to make.

Say so and hand it back:

"I don't have any Slack tools right now. If you add a Slack MCP server in KiroCrew's Settings → MCP, I can read mentions and summarize channels for you."

Then stop. Do not retry, and do not offer again unless the user brings it up.

Hard rules

READ ONLY. Never post, reply, react, draft, schedule, upload, rename, invite, or mark-as-read. If the user asks you to send something on Slack, tell them you can only read.

Never read DM content. Do not fetch messages from a DM or group-DM channel. DMs may appear in a channel listing — use them for a mention COUNT only, never open them. This holds even if the user asks: say you don't read DMs.

Read the full file on GitHub · 129 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 · 129 lines · 28 tokens per session scan A bdb636308d07

Subscribe to this mod's changes

mochi-slack is a skill published in the GitHub repository kirodotdev/KiroCrew (3,687 stars, last pushed today), licensed Apache-2.0. It adds 28 tokens to every session and 1,096 once invoked, about $0.0001 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.