set-copilot: Command for Claude Code

.claude/commands/set/msg.md

msg is a command for Claude Code from tatargabor/set-copilot. It costs 0 tokens per session (330 once invoked), scanned A, original, MIT.

A command for sending a message to another coding agent or team member through the project's shared control area.

In plain words
What is it for?
It is for directing messages to a team member or a specific worktree while working on a shared project.
Why use it?
It avoids manually coordinating separate worktrees and queues the message for the next synchronization cycle.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is tatargabor/set-copilot's own configuration. It tells Claude Code how to work on set-copilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything set-copilot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tatargabor/set-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tatargabor/set-copilot/master/.claude/commands/set/msg.md
Clone the repo
git clone --depth 1 https://github.com/tatargabor/set-copilot

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 msg

README.md
[![agentmods](https://agentmods.dev/badge/commands/tatargabor/set-copilot/msg.svg)](https://agentmods.dev/commands/tatargabor/set-copilot/msg)
Your own site
<a href="https://agentmods.dev/commands/tatargabor/set-copilot/msg"><img src="https://agentmods.dev/badge/commands/tatargabor/set-copilot/msg.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 330 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 5.1 $0.00000 $0.00330
Opus 5 $0.00000 $0.00165
Sonnet 5 $0.00000 $0.00066
Haiku 4.5 $0.00000 $0.00033

Measured yesterday against content hash bc6a90098daa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

msg 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 yesterday.

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/set/msg.md · 30 lines

What it actually says

Send a directed message to another agent or team member.

Usage: /set:msg <recipient> <message>

Input: The first argument is the recipient (e.g., tg@linux or tg@linux/gep2-linux for a specific worktree). The rest is the message text.

What to do:

  1. Parse the arguments: first word is recipient, rest is the message
  2. Find the project's .set-control worktree path:
    • Get the current project from ~/.config/set-core/projects.json
    • The control worktree is at <project_path>/.set-control
  3. Run the send command with --no-push (message will be delivered on next sync cycle):
    set-control-chat --path <project_path> --no-push send <recipient> "<message>"
    
  4. Report success or failure

Important:

  • Uses --no-push so the message is queued locally and delivered on the next sync cycle (~15 seconds)
  • This adds ZERO additional git operations — the existing sync cycle picks up outbox changes
  • For multiline messages, the agent can write to a temp file and pipe it:
    echo "<message>" | set-control-chat --path <project_path> --no-push send <recipient> -
    
  • If recipient has multiple worktrees, specify <member>/<change_id> to target a specific one
  • If recipient is not found, the command will list available members

ARGUMENTS: $ARGUMENTS

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. yesterday First seen · 30 lines · 0 tokens per session scan A bc6a90098daa

Subscribe to this mod's changes

msg is a command published in the GitHub repository tatargabor/set-copilot (2 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 330 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.