message-agent

Send a message to another mngr agent. Use when you need to communicate with a peer agent.

226 stars

Best use case

message-agent is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Send a message to another mngr agent. Use when you need to communicate with a peer agent.

Teams using message-agent should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/message-agent/SKILL.md --create-dirs "https://raw.githubusercontent.com/imbue-ai/mngr/main/.claude/skills/message-agent/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/message-agent/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How message-agent Compares

Feature / Agentmessage-agentStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Send a message to another mngr agent. Use when you need to communicate with a peer agent.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

The user's message contains a target agent name (the first word) and a description of what to communicate. Extract the agent name and treat everything after it as the intent/content of the message.

Your agent name is: !`echo "$MNGR_AGENT_NAME"`

## Agent Name Resolution

Use the `/find-agent` skill with the first word of the user's input to resolve it to an exact agent name.

## Composing the Message

Based on the user's description, compose the full message. Every message you send MUST:

1. **Start with a sender tag**: `[from: !`echo "$MNGR_AGENT_NAME"`]`.
2. **Contain the actual content**: Write the message based on what the user described. Be clear and direct.
3. **End with a reply instruction**: Close with a line like: `To reply, use the /message-agent skill.`

Example message (for an agent named `refactor-auth`):

```
[from: refactor-auth]

Hey -- I just finished refactoring the auth middleware on my branch. You'll want to rebase before merging since I changed the SessionStore interface. The new method is `get_session_by_token()` instead of `lookup()`.

To reply, use the /message-agent skill.
```

## Sending the Message

Write the composed message to a temporary file using the Write tool, then send it with `--message-file`. Name the temp file `/tmp/mngr-message-from-YOUR_NAME-to-AGENT_NAME.txt` (using your agent name and the resolved target name):

```bash
uv run mngr message AGENT_NAME --message-file /tmp/mngr-message-from-YOUR_NAME-to-AGENT_NAME.txt
```

Use `--message-file` for all messages -- it avoids shell quoting issues and preserves formatting.

## After Sending

Report to the user what you sent and to whom. If the send command fails, report the error.

Related Skills

writing-specs

226
from imbue-ai/mngr

Write high quality specifications or design docs for a program. Use any time you are asked to write, improve, or update specs / design docs (e.g., files in a `specs/` folder).

writing-ratchet-tests

226
from imbue-ai/mngr

Write ratchet tests to prevent accumulation of code anti-patterns. Use when asked to create a "ratchet test" for tracking and preventing specific code patterns (e.g., TODO comments, inline imports, broad exception handling).

writing-docs

226
from imbue-ai/mngr

Write high quality, user-facing documentation. Use any time you need to write, improve, or update a significant amount of user-facing documentation (e.g., files in a "docs/" folder or README file).

wait-for-agent

226
from imbue-ai/mngr

Wait for another agent to enter WAITING state, then execute follow-up instructions

update-issues-in-repo

226
from imbue-ai/mngr

Convert a file containing identified issues into a tracked file in current_tasks/. Use after running identify-* commands to create a local record of current issues.

triage-backlog

226
from imbue-ai/mngr

Interactively triage the user's local engineering backlog file into GitHub issues. Use when the user wants to process their raw thought notes / ticket backlog into proper GitHub issues.

think-of-something-to-fix

226
from imbue-ai/mngr

Come up with good ideas about what to fix. Use when you have to fix something, but you're not sure what.

sync-tutorial-to-e2e-tests

226
from imbue-ai/mngr

Match tutorial script blocks to e2e pytest functions and add missing tests

minds-dev-iterate

226
from imbue-ai/mngr

Set up and iterate on the minds app stack (desktop client, workspace server, mngr, forever-claude-template) with a running Docker agent

identify-style-issues

226
from imbue-ai/mngr

Identify divergences from the style guide in the $1 library

identify-outdated-docstrings

226
from imbue-ai/mngr

Identify outdated docstrings in the $1 library

identify-inconsistencies

226
from imbue-ai/mngr

Identify inconsistencies in the $1 library