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.
git clone --depth 1 https://github.com/SaigonXIII/evcWrote 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/commands/saigonxiii/evc/comms-scan)<a href="https://agentmods.dev/commands/saigonxiii/evc/comms-scan"><img src="https://agentmods.dev/badge/commands/saigonxiii/evc/comms-scan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/saigonxiii/evc/comms-scan"><img src="https://agentmods.dev/badge/commands/saigonxiii/evc/comms-scan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00821 |
| Opus 5.5 | $0.00000 | $0.00328 |
| Sonnet 5.5 | $0.00000 | $0.00164 |
| Haiku 4.5 | $0.00000 | $0.00082 |
Grade A, and why
comms-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 1mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comms Scan
Unified communication triage across email, social mentions, and project management in one pass.
Trigger
User invokes /comms-scan or says "check comms", "what needs my attention", "inbox scan", "triage"
Steps
1. Scan all channels in parallel
Launch up to 4 Agent subagents simultaneously (skip any that are not configured):
Agent 1: Social Mentions Check configured social platforms for recent mentions and replies:
- Search for mentions of
{{COMPANY_HANDLE}}in the last 24 hours - Exclude self-posts and known bot accounts
- Capture: author, timestamp, content, engagement metrics
Agent 2: Email Use Gmail MCP (or configured email integration) to search recent unread messages:
gmail_search_messageswith query "is:unread newer_than:1d"- Read top 10 results
Agent 3: Project Management Use Linear MCP (or configured PM tool) to check assigned/mentioned issues:
- Filter to {{PRIMARY_TEAM}} team, updated in last 24h
- Check for new comments on existing issues
Agent 4: Messaging Platforms Check configured messaging platforms (Slack, Discord, LinkedIn) for:
- Direct messages and connection requests
- Comments on company posts
- Classify: partnership inquiries, spam, genuine engagement
2. Classify each item (4 tiers)
| Tier | Action | Examples |
|---|---|---|
| skip | Auto-ignore | Bots, noreply, notifications, spam mentions, mass-tag posts |
| info_only | Summary line | CC'd emails, group chatter, status changes |
| meeting_info | Calendar cross-ref | Zoom links, scheduling requests, .ics files |
| action_required | Draft reply | Direct questions, @mentions with questions, comments needing response |
3. Apply brand-specific filters
For social mentions:
- Skip: accounts with <50 followers, spam, mass-tag engagement farming
- Skip: threads already replied to (check conversation_id)
- Draft replies follow
brand/canon-rules.jsonguardrails
For email:
- Skip: automated notifications from CI/CD, project management, hosting
- Flag: emails from partners ({{PARTNER_LIST}}), investors, or core team
- Flag: scheduling/meeting requests
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.
- 1mo ago First seen · 108 lines · 0 tokens per session scan A 272bbfa592bd
comms-scan is a command published in the GitHub repository SaigonXIII/evc (59 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 821 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.
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.
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.
review-tool
Research a tool or product for skill-gap, architecture, and verb-fit per the Anatomy framework.