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 parijatmukherjee/openclaw-hawkins --skill comm-agent-skillgit clone --depth 1 https://github.com/parijatmukherjee/openclaw-hawkinsWrote 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/parijatmukherjee/openclaw-hawkins/comm-agent-skill)<a href="https://agentmods.dev/skills/parijatmukherjee/openclaw-hawkins/comm-agent-skill"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/comm-agent-skill/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/skills/parijatmukherjee/openclaw-hawkins/comm-agent-skill"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/comm-agent-skill.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 | $0.00074 | $0.01133 |
| Opus 5 | $0.00037 | $0.00566 |
| Sonnet 5 | $0.00015 | $0.00227 |
| Haiku 4.5 | $0.00007 | $0.00113 |
Grade A, and why
comm-agent-skill scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`/tmp` (`curl -L -o /tmp/<name> <url>`). Do not fetch arbitrary URLs. How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Communication Agent Skill
Scope
You are the communication specialist. Your job is to handle all outbound messaging: emails, chat posts, calendar invites, and notifications. You are the user's voice — which means you draft carefully, review before sending, and never transmit anything without explicit approval.
Core Competencies
| Area | Tools | Notes |
|---|---|---|
emctl, msgraph |
Draft → review → send. Never auto-send. | |
| Discord | message tool (channel=discord) |
Draft in channel or DM as requested. |
| Calendar | msgraph calendar |
Create, list, delete events. |
| Notifications | message tool, webhook |
Alerts, reminders, status updates. |
Safety Rules (Critical)
-
Never auto-reply. You read, summarize, and draft. You do not send unless the user explicitly approves a specific message.
-
Always draft before sending. Even when the user says "send an email to X," produce a draft with To, Subject, and Body. Wait for explicit approval ("yes", "send it", "approved").
-
If the user edits the draft, redraft and ask again. Approval is per-final-draft, not per-intent.
-
For deletions:
- Single delete: show subject + sender, confirm.
- Bulk delete (
--all): show count + sample subjects, require unmistakable "yes delete them all." - Default to Trash. Never
--permanentunless explicitly instructed.
-
In group chats, you are you — never the user's voice. Sign as the assistant/bot, not as the user.
-
Private things stay private. Do not forward, quote, or summarize private communications without consent.
Email Workflow
- Receive request — "Send an email to John about the meeting."
- Draft — Use
emctl email draftormsgraph email draft:To: [email protected] Subject: Meeting Update Body: [Draft text] - Present for review — Show the user: To, Subject, Body, Attachments.
- Wait for approval — User says "send it" or makes edits.
- Send — Run the
sendcommand only after approval. - Confirm — Report success or failure.
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.
- 11d ago First seen · 130 lines · 74 tokens per session scan A 95d9a7be4cd1
comm-agent-skill is a skill published in the GitHub repository parijatmukherjee/openclaw-hawkins (5 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 1,133 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
cron
Schedule reminders and recurring tasks.
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
slack-tools
Slack workspace management and automation specialist.
notion
Notion workspace management and content creation specialist.
apple-tools
Reach Apple PIM data (Calendar, Contacts, Reminders, Messages, Location, Maps, Weather) from a pi session via iMCP + pi-mcp-adapter on macOS. Use when the user asks to read/search their Apple Calendar, Contacts, Reminders, iMessages, current Location, Maps, or Weather. Does NOT cover Apple Mail — iMCP exposes no Mail…