slack-message

slack-message is a skill for Claude Code from dgilford/ai-science-toolkit. It costs 41 tokens per session (558 once invoked), scanned A, original, MIT.

A guide for drafting an internal Slack message from the current project state and the user’s intended audience.

In plain words
What is it for?
Preparing status updates, findings, review requests, information notes, or action requests for a teammate or internal channel.
Why use it?
It makes the draft fit the recipient, purpose, tone, length, and requested action instead of guessing those details.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the ai-science-toolkit plugin — 21 skills, 4 agents shipped together

Good fit Preparing status updates, findings, review requests, information notes, or action requests for a teammate or internal channel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dgilford/ai-science-toolkit/slack-message
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 dgilford/ai-science-toolkit --skill slack-message
Clone the repo
git clone --depth 1 https://github.com/dgilford/ai-science-toolkit

Made for: Claude Code.

Or install ai-science-toolkit, the plugin that ships this one along with the rest of its 21 skills, 4 agents.

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-message

README.md
[![agentmods](https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/slack-message.svg)](https://agentmods.dev/skills/dgilford/ai-science-toolkit/slack-message)
Your own site
<a href="https://agentmods.dev/skills/dgilford/ai-science-toolkit/slack-message"><img src="https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/slack-message.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 558 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 $0.00041 $0.00558
Opus 5 $0.00020 $0.00279
Sonnet 5 $0.00008 $0.00112
Haiku 4.5 $0.00004 $0.00056

Measured 7d ago against content hash 984849392eb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

slack-message 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 7d 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.

skills/slack-message/SKILL.md · 52 lines

What it actually says

You are drafting a first-draft Slack message for the user to review and edit before sending. Synthesize live project context with their direction.

Live context

echo "=== Recent commits ===" && git log --oneline -5 2>/dev/null || echo "(not a git repo)"
echo "=== Working state ===" && git status --short 2>/dev/null | head -20 || echo ""
echo "=== Directory ===" && basename "$(pwd)"

Interview

Check the user's request against this list. If any anchor is missing, ask all missing questions in one message — never one at a time.

# Question
1 Who is this for? Name/role; DM, team channel, or leadership post?
2 What's the purpose? (status update / share a finding / request review / ask for action / FYI)
3 What's the one key thing they need to know?
4 Tone: casual or professional? Technical or plain language?
5 Length: one-liner, short paragraph, or structured with sections?
6 Call to action or deadline? What, if anything, do you need from them — and by when?

Drafting rules

  1. Ground the message in the live context above — reference actual recent work, commits, or open changes where relevant (don't invent).
  2. Write in the user's voice: direct, no corporate hedging.
  3. Use Slack-native formatting: *bold*, _italic_, bullet lists with -, ```code``` blocks for technical snippets.
  4. Scale technical depth to the audience: peer-level can go deep; leadership stays outcome-focused.
  5. One message, one point. If the user has multiple asks, flag that and suggest splitting.
  6. Always generate a Title — a short (≤10 word) subject line that captures the message purpose. Always end the title with 🔽.

Output

Present the draft with a title line followed by the message body inside a fenced block:

Title: <title ending with 🔽>

<!-- Slack draft -->
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. 7d ago First seen · 52 lines · 41 tokens per session scan A 984849392eb6

Subscribe to this mod's changes

slack-message is a skill published in the GitHub repository dgilford/ai-science-toolkit (62 stars, last pushed 18d ago), licensed MIT. It adds 41 tokens to every session and 558 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 2026-08-30.