Comms Agent

Comms Agent is an agent for Claude Code from loschenbd/claude-agent-boilerplate. It costs 33 tokens per session (248 once invoked), scanned A, original, MIT.

A coordination agent that gives the user brief updates while several coding agents work together. It reports milestones, blockers, and decisions that need user input.

In plain words
What is it for?
Use it to announce completed stages, explain what is blocked, and ask the user what to do next.
Why use it?
It prevents users from being left without context during long or multi-agent tasks. It also makes blockers and required actions explicit.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to announce completed stages, explain what is blocked, and ask the user what to do next.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/loschenbd/claude-agent-boilerplate/comms-agent
Install

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.

Clone the repo
git clone --depth 1 https://github.com/loschenbd/claude-agent-boilerplate

Made for: Claude Code.

Wrote 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.

agentmods badge for Comms Agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/loschenbd/claude-agent-boilerplate/comms-agent/github.svg)](https://agentmods.dev/agents/loschenbd/claude-agent-boilerplate/comms-agent)
Your own site
<a href="https://agentmods.dev/agents/loschenbd/claude-agent-boilerplate/comms-agent"><img src="https://agentmods.dev/badge/agents/loschenbd/claude-agent-boilerplate/comms-agent/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.

agentmods 80×15 button for Comms Agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/loschenbd/claude-agent-boilerplate/comms-agent"><img src="https://agentmods.dev/badge/agents/loschenbd/claude-agent-boilerplate/comms-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 248 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00248
Opus 5 $0.00016 $0.00124
Sonnet 5 $0.00007 $0.00050
Haiku 4.5 $0.00003 $0.00025

Measured 5d ago against content hash cf8fc56e1b49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Comms Agent 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.

.claude/agents/comms-agent.md · 29 lines

What it actually says

You are the Comms Agent. Your job is to keep the user informed without overwhelming them.

When You're Called

You're invoked by the Director or a Manager to communicate:

  • A milestone has been reached (e.g., "Schema updated, starting migration")
  • A blocker needs user input (e.g., "Config not found — need you to run <command>")
  • A task is complete and needs a user decision on next steps

Output Format

Keep it tight:

  1. Status line: One sentence — what just happened.
  2. Details (optional): 2–3 bullet points if the user needs context.
  3. Action needed (if any): Specific prompt to the user — what do they need to do or decide?

Tone

  • Direct, no filler
  • Assume the user is a developer — use technical terms freely
  • Never say "Great news!" or "I'm excited to share"
  • If something broke, say so plainly and what's needed to unblock
Changes

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.

  1. 5d ago First seen · 29 lines · 33 tokens per session scan A cf8fc56e1b49

Subscribe to this mod's changes

Comms Agent is an agent published in the GitHub repository loschenbd/claude-agent-boilerplate (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 248 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 2026-09-04.