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.
npx skills add sepehr500/skills --skill slackgit clone --depth 1 https://github.com/sepehr500/skillsWrote 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.
[](https://agentmods.dev/skills/sepehr500/skills/slack)<a href="https://agentmods.dev/skills/sepehr500/skills/slack"><img src="https://agentmods.dev/badge/skills/sepehr500/skills/slack.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00036 | $0.01221 |
| Opus 5 | $0.00018 | $0.00611 |
| Sonnet 5 | $0.00007 | $0.00244 |
| Haiku 4.5 | $0.00004 | $0.00122 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Integration
Interact with Slack on the user's behalf using the Python Slack SDK - read messages, send replies, download and upload files.
Setup
Ensure the Python Slack SDK is installed:
pip install slack-sdk
Authentication
Use the Slack token from $SLACK_TOKEN environment variable. If not available, ask the user to provide it.
Required scopes (add via https://api.slack.com/apps -> OAuth & Permissions -> User Token Scopes):
search:read- search messages and files (preferred method)users:read- look up users (required forusers.list)users:read.email- access email addresses in user profiles (optional)im:history,im:read- read DMsim:write,chat:write- send messageschannels:history,channels:read- read channels (optional)files:read- download filesfiles:write- upload files
Python Slack SDK Client
A reusable client module is available at ~/.claude/skills/slack/scripts/slack_client.py.
CLI Usage
# Test authentication
python ~/.claude/skills/slack/scripts/slack_client.py auth
# Search messages
python ~/.claude/skills/slack/scripts/slack_client.py search "from:me to:username" --count 5
# List users
python ~/.claude/skills/slack/scripts/slack_client.py users
# Find a user by name
python ~/.claude/skills/slack/scripts/slack_client.py find-user "Alice"
# List conversations (DMs)
python ~/.claude/skills/slack/scripts/slack_client.py conversations --types im
# Get DM channel with user
python ~/.claude/skills/slack/scripts/slack_client.py dm-channel U12345
# Read messages from channel
python ~/.claude/skills/slack/scripts/slack_client.py read D67890 --limit 10
# Send a message
python ~/.claude/skills/slack/scripts/slack_client.py send D67890 "Hello there!"
Module Usage (inline Python)
import sys
sys.path.insert(0, str(Path.home() / ".claude/skills/slack/scripts"))
from slack_client import (
test_auth, search_messages, list_users, find_user,
get_dm_channel, read_messages, send_message,
get_file_info, download_file, upload_file
)
# Test auth
auth = test_auth()
print(f"Authenticated as {auth['user']}")
# Search messages
messages = search_messages("from:me to:alice", count=5)
for msg in messages:
print(f"{msg['ts']}: {msg['text']}")
# Find user and send message
user = find_user("Alice")
if user:
channel = get_dm_channel(user['id'])
result = send_message(channel, "Hello Alice!")
print(f"Sent message: {result['ts']}")
What ships with it
1 file 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.
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.
- 8d ago First seen · 159 lines · 36 tokens per session scan A 27be272b9a67
slack is a skill published in the GitHub repository sepehr500/skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 1,221 once invoked, about $0.0002 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.
Other skills, from other repositories
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…
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.