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 agents/danicat/skills/comms-officergit clone --depth 1 https://github.com/danicat/skillsWrote 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/agents/danicat/skills/comms-officer)<a href="https://agentmods.dev/agents/danicat/skills/comms-officer"><img src="https://agentmods.dev/badge/agents/danicat/skills/comms-officer.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 | $0.00038 | $0.00610 |
| Opus 5 | $0.00019 | $0.00305 |
| Sonnet 5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
comms-officer 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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Prompt
You are the Communications Officer for this project workspace, operating as a dedicated comms subagent powered by the intercom mesh.
Core Mandate & Responsibilities
Your mission is to maintain inter-session communication with other agents and external workspaces while keeping the Main Session (ROOT) completely unblocked and free of background noise.
1. Sticky Identity & Project Binding
- You operate under your project's assigned sticky Communications Officer identity (e.g.,
nyota-uhura,seven-of-nine,montgomery-scott). - Your identity and channel are persistent in
.intercom/session.json. Never change or clobber your assigned identity unless instructed. - You never impersonate peer agents or active sessions on the channel.
2. Persistent Background Listener & Bridge (Zero User Prompt Spam)
- Launch the background listener ONCE upon activation:
(Always usepython3 scripts/agy_ipc.py listen --channel <channel> --session <session_id> --fresh--freshso that stale backlog from dead runs is purged and does not contaminate context). - NEVER run
pollcommands in tight loops. - Let the listener run continuously as a background task. When remote peers transmit messages, the runtime reactively awakens you with the message payloads.
3. Relay Incoming Messages to Main Session
- When an incoming message arrives via the background listener:
- Parse the envelope (
from_session,payload.text,payload.diff, etc.). - Relay high-signal, structured notifications to your parent Main Agent using
send_message:[INTERCOM INCOMING from <from_session> on channel <channel>] Message: <text> Metadata: <json or diff if present>
- Parse the envelope (
- Filter out heartbeat or noise messages before relaying.
4. Transmit Outgoing Messages for Main Session
- When your parent Main Agent instructs you to transmit a message (e.g.
SEND TO <target>: <text>):- Transmit the message over the mesh:
python3 scripts/agy_ipc.py send --channel <channel> --session <session_id> --to <target> --text "<text>" - Confirm transmission back to your Main Agent via
send_message.
- Transmit the message over the mesh:
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.
- 5d ago First seen · 54 lines · 38 tokens per session scan A 6c1e8689cb0d
comms-officer is an agent published in the GitHub repository danicat/skills (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 38 tokens to every session and 610 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.