Kagura: Skill for Claude Code

.claude/skills/slack/SKILL.md

slack is a skill for Claude Code from Innei/Kagura. It costs 97 tokens per session (2,834 once invoked), scanned A, original, MIT.

A read-only assistant for finding and examining information in Slack, a workplace messaging service. It can work with messages, threads, channels, users, and shared files when the required Slack access is available.

In plain words
What is it for?
Use it to open Slack message links, read thread replies, search conversation history, identify users or channels from names and IDs, and download shared logs, screenshots, CSV files, or PDFs.
Why use it?
It removes the need to manually search through conversations or decode Slack links and IDs when investigating a bug, decision, or incident.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Innei/Kagura's own configuration. It tells Claude Code how to work on Kagura 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 Kagura configures →

View source ↗ Innei/Kagura
Reuse

Borrowing it

Nothing to install: this file belongs to Innei/Kagura. 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/Innei/Kagura/main/.claude/skills/slack/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Innei/Kagura

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/innei/kagura/slack/github.svg)](https://agentmods.dev/skills/innei/kagura/slack)
Your own site
<a href="https://agentmods.dev/skills/innei/kagura/slack"><img src="https://agentmods.dev/badge/skills/innei/kagura/slack/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/innei/kagura/slack"><img src="https://agentmods.dev/badge/skills/innei/kagura/slack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,834 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00097 $0.02834
Opus 5 $0.00048 $0.01417
Sonnet 5 $0.00019 $0.00567
Haiku 4.5 $0.00010 $0.00283

Measured 10d ago against content hash f339fb3828d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

slack scanned grade A with 1 finding 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 10d ago.

The scan reads SKILL.md. This mod also ships 26 executable files (scripts/sk/__init__.py, scripts/sk/cache.py, scripts/sk/channels.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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| 依赖 | **无**(只用标准库 `urllib`,零 `pip install`) |
.claude/skills/slack/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slack Skill

只读 Slack Web API 的 9 个子命令封装,统一入口 scripts/slack.py不写消息 / 不加 reaction / 不 mark-read —— 这些动作由调用方 Bot 自己处理,client 层有硬编码白名单拦截。


When to Use

触发信号(AI 看到任一信号即考虑调用):

  • https://*.slack.com/archives/... 链接
  • C[A-Z0-9]{8,} / U[A-Z0-9]{8,} / D[A-Z0-9]{8,} / F[A-Z0-9]{8,} 风格 ID
  • p123456789012345 风格的消息 ts
  • 用户提到 "Slack" / "thread" / "频道" / "群里" / "@某人 在 Slack 说"
  • Jira/PR 正文里的 Slack permalink(排查类任务需要 QA/RD 讨论上下文)

术语对照

用户说法 含义
slack / 消息 / DM / 频道 / thread / permalink 本 skill
Slack URL https://xxx.slack.com/archives/... get / replies / files_download --url 入参
@handle / @name / #channel / ^subteam resolve / users / channels 入参
ts / thread_ts Slack 时间戳 ID(1234567890.123456

Quick Reference

入口

.agent-slack/skills/slack/scripts/slack.py

查找顺序:./.agent-slack/skills/slack/scripts/slack.py<git-root>/.agent-slack/skills/slack/scripts/slack.py<git-root>/slack/scripts/slack.py(仓库开发路径)→ find . -path '*skills/slack/scripts/slack.py'

所有调用 = python3 <path> <subcommand> [flags]禁止 import sk.* 绕过入口。

子命令表

子命令 作用 典型入参
get 读单条消息 --url <permalink>
replies 读整个 thread --url <任一消息 permalink>
history 浏览频道最近消息 --channel <#name|C...> --limit <n|1d|2h>
search 全域搜消息(xoxp 专属) <query 字符串,原生 modifier>
files_download 下附件 --file-id F...--url <permalink>
channels 搜/列频道(走 cache) --query <name> / --type public
users 查人(ID/email/name) --id U... / --email ... / --query <name>
resolve 字符串 → 对象 resolve "#eng" / "@alice" / "^oncall" / U.../C.../F.../email
cache_refresh 刷本地 users/channels/subteams 字典

每条都支持 --help。大输出用 --output <file>(stdout 只打 saved: <path>)。


Setup

说明
Python ≥ 3.9
依赖 (只用标准库 urllib,零 pip install
配置 复制 slack/.env.exampleslack/.env,至少填 SLACK_BOT_TOKEN

Read the full file on GitHub · 193 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. 10d ago First seen · 193 lines · 97 tokens per session scan A f339fb3828d5

Subscribe to this mod's changes

slack is a skill published in the GitHub repository Innei/Kagura (52 stars, last pushed 3d ago), licensed MIT. It adds 97 tokens to every session and 2,834 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

metaschedule

MetaBot's persistent server-side scheduler (cron + one-shot). Optional skill — not installed by default. Use when the user wants tasks that survive Claude session restarts, are visible to other bots, or need to run in MetaBot's PM2 process rather than this Claude session.

xvirobotics/metabot · 61 tokens

metabot-team

Use for the MetaBot Agent Teams CLI: create and inspect durable Teams, spawn teammates, exchange messages, and manage Tasks and Runs across Sessions.

xvirobotics/metabot · 33 tokens

metabot

Unified MetaBot CLI for personal Memory, Skill Hub, durable Agent Bus messaging, agent registry, Agent Teams, T5T, scheduling, and bridge runtime operations.

xvirobotics/metabot · 36 tokens

metaskill

The meta-skill: create AI agent teams, individual agents, or custom skills for any project. Use when the user wants to generate a complete agent team, create a single agent, or create a single skill for Claude Code, Kimi, or Codex.

xvirobotics/metabot · 57 tokens

access

Manage Slack channel access control — pairing, allowlist, channel opt-in. Use when approving a pairing code, changing the DM policy, editing the user allowlist, or opting a channel in or out. Trigger with "/slack-channel:access", "pair my slack account", "add user to slack allowlist", or "opt in a slack channel".

jeremylongshore/claude-code-slack-channel · 74 tokens

install

Detect installation failures and install, verify, repair, reset, or uninstall the CCSC Slack channel. Use when setting up the Slack channel, checking an existing installation, exporting its Slack app manifest, or safely tearing it down. Trigger with "/slack-channel:install", "install the slack channel", "slack channel…

jeremylongshore/claude-code-slack-channel · 76 tokens