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/saigonxiii/evc/slack-commsgit clone --depth 1 https://github.com/SaigonXIII/evcWhat 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 | $0.00000 | $0.01370 |
| Opus 5 | $0.00000 | $0.00685 |
| Sonnet 5 | $0.00000 | $0.00274 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
slack-comms 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Comms
Read, write, and manage Slack communications. Supports reading channel history, posting messages, summarizing threads, replying in threads, and posting structured action notifications.
Trigger
User invokes /slack-comms <CHANNEL> <ACTION> or says "check Slack", "post to Slack", "summarize channel"
Actions:
read— Fetch recent messages from a channelpost <message>— Compose and post a messagesummarize— Digest recent activity into key pointsthread <ts> <message>— Reply in a specific threadnotify <action-summary>— Post an action notification with status
Examples:
/slack-comms #engineering read
/slack-comms #general post Shipped the new landing page — link in thread
/slack-comms #general summarize
/slack-comms #engineering thread 1234567890.123456 Updated the PR
/slack-comms #updates notify Created 3 tickets from today's meeting
Read Mode
Fetch and present recent messages from a channel.
- Retrieve the last 20 messages (or user-specified count).
- For each message, extract: author, timestamp, text, thread reply count.
- Present in a readable format:
### #<channel> — Recent Messages
| Time | Author | Message | Threads |
|---|---|---|---|
| 10:23 | Alice | Meeting moved to Thursday | 3 replies |
| 10:45 | Bob | Updated the deck — link in thread | 1 reply |
| 11:02 | Slackbot | Reminder: standup in 15 min | — |
If Slack MCP is available: Use Slack MCP tools to fetch messages. If not available: Ask the user to paste the messages or provide a channel export.
Post Mode
Compose and post a message to a channel.
Composition Guidelines
- Professional but conversational. Match {{COMPANY_NAME}}'s internal tone.
- Lead with the action or decision. Don't bury the point.
- Use emoji for status:
- :white_check_mark: Done / Approved
- :warning: Blocked / Needs attention
- :question: Needs input / Unclear
- :rocket: Shipped / Deployed
- :memo: Draft / For review
- Link to tickets and PRs. Use full URLs for issues and PRs.
- Keep it concise. Slack messages should be scannable, not essays.
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 · 210 lines · 0 tokens per session scan A 10b80c1ff6e2
slack-comms is a command published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,370 tokens. 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
weekly-review
Weekly review — read the week's logs, surface patterns, set next week's one priority.
morning-briefing
Recap yesterday, surface priorities, set today's top three.
capture
Capture a raw thought now; triage it to the right place later.
demo-briefing
Run the full morning ritual against the fictional demo/ data — a safe way to see it work, and a safe thing to present from.
end-of-day
Close the day — log what happened, tee up tomorrow.
midday-checkin
Mid-day reset — what's done, what's slipping, what to protect this afternoon.