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 dgilford/ai-science-toolkit --skill slack-messagegit clone --depth 1 https://github.com/dgilford/ai-science-toolkitWrote 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/dgilford/ai-science-toolkit/slack-message)<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>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 | $0.00041 | $0.00558 |
| Opus 5 | $0.00020 | $0.00279 |
| Sonnet 5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
slack-message scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are drafting a first-draft Slack message for the user to review and edit before sending. Synthesize live project context with their direction.
Live context
echo "=== Recent commits ===" && git log --oneline -5 2>/dev/null || echo "(not a git repo)"
echo "=== Working state ===" && git status --short 2>/dev/null | head -20 || echo ""
echo "=== Directory ===" && basename "$(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
- Ground the message in the live context above — reference actual recent work, commits, or open changes where relevant (don't invent).
- Write in the user's voice: direct, no corporate hedging.
- Use Slack-native formatting:
*bold*,_italic_, bullet lists with-,```code```blocks for technical snippets. - Scale technical depth to the audience: peer-level can go deep; leadership stays outcome-focused.
- One message, one point. If the user has multiple asks, flag that and suggest splitting.
- 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 -->
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.
- 7d ago First seen · 52 lines · 41 tokens per session scan A 984849392eb6
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.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
omh-morning-brief
This is a Hermes-native morning-brief workflow skill.
omh-deliverable-package
This is a Hermes-native deliverable-package workflow skill.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.