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 agentmods add commands/slackapi/slack-skills-plugin/draft-announcementgit clone --depth 1 https://github.com/slackapi/slack-skills-pluginWhat 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 | $0.00013 | $0.00333 |
| Opus 5 | $0.00006 | $0.00167 |
| Sonnet 5 | $0.00003 | $0.00067 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade A, and why
draft-announcement 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 3d 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
Given the topic or context provided in $ARGUMENTS:
-
Ask the user the following clarifying questions (skip any that are already clear from the provided context):
- Which channel should this announcement be posted in?
- Who is the target audience?
- What is the key message or call to action?
- Is there a deadline or date to highlight?
- What tone is appropriate — formal, casual, or urgent?
-
Compose the announcement following Slack formatting best practices:
- Use standard markdown:
**bold**for emphasis,_italic_for secondary emphasis,>for callouts. - Lead with the most important information — don't bury the point.
- Use a clear, descriptive opening line that works as a headline.
- Keep paragraphs short (2-3 sentences max).
- Use bullet points for lists of items or action steps.
- Include relevant emoji sparingly to aid scanning (e.g., :mega: for announcements, :calendar: for dates, :point_right: for action items).
- End with a clear call to action or next step if applicable.
- Use standard markdown:
-
Present the draft to the user for review. Offer to adjust tone, length, or formatting.
-
Once the user approves, use
slack_search_channelsto find the target channel ID, then useslack_send_message_draftto create the draft in Slack. -
Let the user know the draft is ready in Slack and they can review and send it from the Slack client.
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.
- 3d ago First seen · 28 lines · 13 tokens per session scan A d7f5046a8da0
draft-announcement is a command published in the GitHub repository slackapi/slack-skills-plugin (113 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 333 once invoked, about $0.0001 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 commands, from other repositories
build
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
webperf
Run a web performance audit via the web-performance-auditor persona.
spec
Start spec-driven development — write a structured specification before writing code.
install
Add skills from GitHub repos, git URLs, or local paths.
audit-rules
Browse, enable, disable, and customize audit rules.
init
First-time setup. Auto-detects installed AI CLIs and configures targets.