slack-scan

slack-scan is a command for Claude Code from superuser-pal/awesome-second-brain. It costs 0 tokens per session (472 once invoked), scanned A, a copy of om-slack-scan, MIT.

A command for examining Slack channels and direct messages for all messages related to a person or project. Slack is a workplace messaging service where conversations are organized into channels and private messages.

In plain words
What is it for?
Use it to build a dated record of technical work, leadership, collaboration, problem-solving, or initiative across selected Slack conversations.
Why use it?
It collects scattered evidence with timestamps and surrounding context, making it easier to review work or document a project accurately.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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.

agentmods
npx agentmods add commands/superuser-pal/awesome-second-brain/slack-scan
Clone the repo
git clone --depth 1 https://github.com/superuser-pal/awesome-second-brain

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-scan

README.md
[![agentmods](https://agentmods.dev/badge/commands/superuser-pal/awesome-second-brain/slack-scan.svg)](https://agentmods.dev/commands/superuser-pal/awesome-second-brain/slack-scan)
Your own site
<a href="https://agentmods.dev/commands/superuser-pal/awesome-second-brain/slack-scan"><img src="https://agentmods.dev/badge/commands/superuser-pal/awesome-second-brain/slack-scan.svg" alt="Measured on agentmods" 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 472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00472
Opus 5 $0.00000 $0.00236
Sonnet 5 $0.00000 $0.00094
Haiku 4.5 $0.00000 $0.00047

Measured 6d ago against content hash 9c2d864c7357, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

slack-scan 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 6d 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.

Origin

This is a copy

89% identical to om-slack-scan — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/capture/slack-scan.md · 52 lines

What it actually says

Slack Deep Scan

Deep scan Slack channels and DMs for evidence involving a specific person or project. Extracts every touchpoint with timestamps for review evidence or project documentation.

Usage

/slack-scan <target> [channels...] [date-range]

Examples:

  • /slack-scan "Jane Doe" C0EXAMPLE1 C0EXAMPLE2 "after:2026-03-16"
  • /slack-scan "project:example" C0EXAMPLE1 C0EXAMPLE2 C0EXAMPLE3 C0EXAMPLE4

Workflow

  1. Read each channel fully (paginate with cursor until all messages are fetched):

    mcp slack_read_channel channel_id=<id> limit=100
    
  2. Search for the person across public+private channels:

    mcp slack_search_public_and_private query="from:<@USER_ID> after:<date>"
    mcp slack_search_public_and_private query="<Name> after:<date> -from:<@USER_ID>"
    
  3. Check DMs the user points to. Read full history for the relevant period.

  4. For each message involving the target, extract:

    • Timestamp and channel
    • What was said/done
    • Context (what prompted it, what followed)
    • Whether it's evidence of: technical work, leadership, collaboration, problem-solving, initiative
  5. Organize by date with clear headers per day. Separate:

    • Project evidence → goes to the relevant work note
    • review/personal context → goes to people notes or review prep notes
    • Team dynamics → goes to people notes
  6. Flag items that need correction in existing vault notes.

Important

  • Be meticulous — timestamps matter for evidence
  • Capture exact quotes when they show initiative, leadership, or problem-solving
  • Note when the person was tagged by others (shows they're a go-to person)
  • Separate project work from review prep from personal conversations
  • Don't mix contexts — put data where it belongs in the vault
  • Check for threads (slack_read_thread) when a message has replies
  • Look for screen recordings, files shared, PRs linked
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. 6d ago First seen · 52 lines · 0 tokens per session scan A 9c2d864c7357

Subscribe to this mod's changes

slack-scan is a command published in the GitHub repository superuser-pal/awesome-second-brain (14 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 472 tokens. A static security scan graded it A with 0 findings. It is 89% identical to om-slack-scan, differing in 8 lines, and is treated as a copy.