broadcast-chat

broadcast-chat is a command for Claude Code from DimitriGeelen/agentic-engineering-framework. It costs 0 tokens per session (1,238 once invoked), scanned A, original, Apache-2.0.

Wraps scripts/chat-arc-broadcast.sh. The "tell the fleet" verb that completes the doorbell+mail interactive arc alongside the read-only discovery skills. This skill mutates state (posts a real envelope to every hub) — pair with /recent-chat for read-side context BEFORE firing, never after.

Command for Claude Code

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.

agentmods
npx agentmods add commands/dimitrigeelen/agentic-engineering-framework/broadcast-chat
Clone the repo
git clone --depth 1 https://github.com/DimitriGeelen/agentic-engineering-framework

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 broadcast-chat

README.md
[![agentmods](https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/broadcast-chat.svg)](https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/broadcast-chat)
Your own site
<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/broadcast-chat"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/broadcast-chat.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,238 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01238
Opus 5 $0.00000 $0.00619
Sonnet 5 $0.00000 $0.00248
Haiku 4.5 $0.00000 $0.00124

Measured today against content hash c56624ed2666, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

broadcast-chat 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 today.

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/commands/broadcast-chat.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/broadcast-chat — fan a chat-arc post to every hub in the fleet (T-1856 wrapper)

Wraps scripts/chat-arc-broadcast.sh. The "tell the fleet" verb that completes the doorbell+mail interactive arc alongside the read-only discovery skills. This skill mutates state (posts a real envelope to every hub) — pair with /recent-chat for read-side context BEFORE firing, never after.

agent-chat-arc does NOT federate (G-060). Without explicit cross-post a chat-arc message lands on one hub only and peers on other hubs never see it. This skill is the operator's one-keystroke fix.

Invocation:

Form Action
/broadcast-chat <text> Post <text> to every hub in ~/.termlink/hubs.toml
/broadcast-chat --from ID --payload "..." Override sender; pass-through flag form
/broadcast-chat --hubs-file PATH ... Custom hubs.toml
/broadcast-chat --json --payload "..." Machine-readable envelope

The wrapper auto-resolves sender via:

  1. --from flag
  2. $TERMLINK_AGENT_ID env
  3. ~/.termlink/be-reachable.state (from /be-reachable)
  4. Exit 2 with hint if all four fail

Step 1: Pre-flight

Run:

bash scripts/chat-arc-broadcast.sh --help >/dev/null 2>&1

If exit non-zero: stop. Print:

broadcast-chat: wrapper not found at scripts/chat-arc-broadcast.sh.
Ensure you're in the TermLink project root (cd /opt/termlink).

Step 2: Parse arguments

$ARGUMENTS is the operator's tail. Normalize:

  • If $ARGUMENTS starts with --: treat the whole thing as pass-through flags. The wrapper validates and errors with usage on malformed input. Do NOT auto-construct --payload in this branch.
  • Otherwise: treat the entire $ARGUMENTS as the broadcast text and pass it as --payload "$ARGUMENTS".

Examples:

Operator typed Command emitted
/broadcast-chat heads up team, I'm back online bash scripts/chat-arc-broadcast.sh --payload "heads up team, I'm back online"
/broadcast-chat --from claude-alt --payload "..." pass-through
/broadcast-chat --hubs-file /tmp/hubs.toml --payload "..." pass-through
/broadcast-chat --json --payload "..." pass-through

Read the full file on GitHub · 126 lines

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. today First seen · 126 lines · 0 tokens per session scan A c56624ed2666

Subscribe to this mod's changes

broadcast-chat is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (13 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,238 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 2026-09-04.