agmsg

agmsg is a skill for Claude Code from fujibee/agmsg. It costs 52 tokens per session (13,800 once invoked), scanned B, original, MIT.

A local messaging system for exchanging messages between coding agents such as Claude Code, Codex, Gemini CLI, and GitHub Copilot CLI.

In plain words
What is it for?
Use it to join an agent team, send messages to other agents, and coordinate work through the provided shell scripts.
Why use it?
It gives agents a shared way to coordinate without a network service or extra dependencies. The messages and team information are stored in SQLite, a small local database.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Part of the agmsg plugin — 1 skill shipped together

Good fit Use it to join an agent team, send messages to other agents, and coordinate work through the provided shell scripts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fujibee/agmsg/agmsg
About the project

agmsg is a cross-agent messaging tool that lets separate command-line AI coding sessions exchange messages through a shared local SQLite database. Developers use it to coordinate Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, and other CLI agents without a daemon or network service, and the catalogue entries provide its related skill and plugin.

fujibee/agmsg · 1,579 stars · on GitHub · producthunt.com

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.

Any agent
npx skills add fujibee/agmsg --skill agmsg
Clone the repo
git clone --depth 1 https://github.com/fujibee/agmsg

Made for: Claude Code.

Or install agmsg, the plugin that ships this one along with the rest of its 1 skill.

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 agmsg

README.md
[![agentmods](https://agentmods.dev/badge/skills/fujibee/agmsg/agmsg/github.svg)](https://agentmods.dev/skills/fujibee/agmsg/agmsg)
Your own site
<a href="https://agentmods.dev/skills/fujibee/agmsg/agmsg"><img src="https://agentmods.dev/badge/skills/fujibee/agmsg/agmsg/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 agmsg

Your own site · 80×15
<a href="https://agentmods.dev/skills/fujibee/agmsg/agmsg"><img src="https://agentmods.dev/badge/skills/fujibee/agmsg/agmsg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,800 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00052 $0.13800
Opus 5.5 $0.00021 $0.05520
Sonnet 5.5 $0.00010 $0.02760
Haiku 4.5 $0.00005 $0.01380

Measured 5d ago against content hash 5c1eb4710162, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agmsg scanned grade B with 2 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.

The scan reads SKILL.md. This mod also ships 42 executable files (scripts/actas-claim.sh, scripts/api.sh, scripts/arrange.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Permission prompts.** Every command here runs through the Bash tool, so each call is gated by the permission system until the script directory is allowlisted. Without this the user is asked to confirm essentially every

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Then ask the user: "Shall I read the files that will run and check them for anything risky before you decide?" If yes, read every file under "Files to read:" in the "Review copy:" directory the printout names — that copy
SKILL.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Step 0: First-run bootstrap

agmsg keeps its SQLite database, team registry, and runtime state under ~/.agents/skills/agmsg/. The ./install.sh install path creates that tree; the Claude Code plugin install path does not (the plugin marketplace only copies this repository into ~/.claude/plugins/cache/). Before any other command, bootstrap if needed:

if [ ! -d ~/.agents/skills/agmsg ]; then
  # Newest cached copy of the plugin. Several versions can sit side by side, so
  # pick by version folder name (numeric, portable -- not sort -V, not mtime).
  cache="$HOME/.claude/plugins/cache/fujibee-agmsg/agmsg"
  newest=$(ls "$cache" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n | tail -1)
  installer="$cache/$newest/install.sh"
  if [ -n "$newest" ] && [ -f "$installer" ]; then
    bash "$installer" --cmd agmsg
  else
    echo "agmsg not installed. Either:" >&2
    echo "  - run ./install.sh in the agmsg repo, or" >&2
    echo "  - install via /plugin marketplace add fujibee/agmsg && /plugin install agmsg@fujibee-agmsg" >&2
    exit 1
  fi
fi

Once ~/.agents/skills/agmsg/ exists this step does nothing, so it is safe to run every time.

Agent messaging command. IMPORTANT: Always use the provided scripts. NEVER directly read or edit config files, DB, or team data. There is NO register.sh — use join.sh to join a team.

Use agmsg, not the host agent's own inter-session messaging. Several agent CLIs ship a native way for one session to message another on the same machine (in Claude Code, the SendMessage / ListAgents tools over its peer-session list). While a project is on agmsg, route agent-to-agent messages through agmsg instead. A message sent natively does not exist as far as agmsg is concerned: it is absent from history.sh and the team's export, it never reaches a member on another machine through remote sync, it does not mark read or advance any cursor, and it cannot address a member whose CLI is a different type. Half the conversation living somewhere unrecorded is worse than either channel alone, and the gap is invisible until someone reads the history and finds a decision with no message behind it. The native channel stays fine for anything outside the team — a subagent you spawned for your own task, or a session that has not joined.

Shell requirement: All agmsg scripts are Bash scripts. Always execute them via bash, never via PowerShell or cmd directly. If your default shell is not Bash (e.g. PowerShell on Windows), wrap every command with bash -lc '...'. Example: bash -lc '~/.agents/skills/agmsg/scripts/send.sh myteam alice bob "hello"'. Do NOT construct DB paths manually — the scripts handle path resolution internally. If you need to redirect storage, use AGMSG_STORAGE_PATH (the supported override).

Read the full file on GitHub · 440 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 Changed · +2 lines 5c1eb4710162
  2. 8d ago Changed · +2 lines 531a50ce3bd5
  3. 11d ago Changed · +16 lines e3c317a7f927
  4. 14d ago Changed · +1 lines 5389096c037a
  5. 16d ago Changed · +11 lines · +13 tokens per session ec52a3761602
  6. 1mo ago Changed · +4 lines bfa5e800fb14
  7. 1mo ago Changed e375382947f0
  8. 1mo ago Changed 2f2ee0760e99
  9. 1mo ago Changed · +94 lines · -2 tokens per session scan A → B 2b0c0b144035
  10. 1mo ago First seen · 310 lines · 41 tokens per session scan A d8de64058b1d

Subscribe to this mod's changes

agmsg is a skill published in the GitHub repository fujibee/agmsg (1,579 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 13,800 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

agmsg compared with skills from other repositories

agmsg next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agmsgfujibee/agmsgSkill1.6ktodayMITB52Claude Code
add-channelaspasskiy/GoGogotSkill26410d agoMITA62Claude Code, Codex
telegramaspasskiy/GoGogotSkill26410d agoMITA45Claude Code, Codex
developmentfengshao1227/ccg-workflowSkill6.0k5d agoMITA41Claude Code
communicationagentscope-ai/AgentTeamsSkill6.0ktodayApache-2.0A36Claude Code, Codex
writing-relayflowsAgentWorkforce/relaySkill1.1ktodayApache-2.0A184Claude Code, Codex
test-warp-uiwarpdotdev/warpSkill66ktodayAGPL-3.0A55Claude Code