agmsg

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 CodeCodex

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 skills/fujibee/agmsg/agmsg
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, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,384 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00045 $0.05384
Opus 5 $0.00023 $0.02692
Sonnet 5 $0.00009 $0.01077
Haiku 4.5 $0.00005 $0.00538

Measured yesterday against content hash da482d6b0853, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

Reads agent configuration directoriesmediumAgent snooping

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

Every agmsg step above runs through the host's Bash tool, so on Claude Code each call is gated by the permission system until you allowlist the script directory. Add these to `~/.claude/settings.json` (or project-level `

Makes network callslowCapability

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

- **Dependencies**: bash, sqlite3 (no python3 required) for core messaging; `remote`/`key` additionally need `curl`, `python3`, and `age`/`age-keygen`, but only if those commands are used
SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Messaging

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.

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).

How to use

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 flow only drops the skill content into ~/.claude/plugins/cache/). Before any other command, bootstrap if needed:

if [ ! -d ~/.agents/skills/agmsg ]; then
  # Locate the plugin install script (any version), run it once.
  installer=$(ls ~/.claude/plugins/cache/fujibee-agmsg/agmsg/*/install.sh 2>/dev/null | head -1)
  if [ -n "$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

After this runs once, ~/.agents/skills/agmsg/ is populated and you can skip Step 0 on future invocations.

Step 1: Check identity

~/.agents/skills/agmsg/scripts/whoami.sh "$(pwd)" <type>
# type: claude-code, codex, gemini, antigravity, copilot
# Returns: agent=... / multiple=true ... / suggest=true ... / not_joined=true ...

Step 2a: If not in a team — join one

Before first-time setup, inspect the user's request. If they ask to join, import, or bring in a team that already exists on a server, do not run join.sh. Go directly to the remote pull command under Step 2b. Before pulling, run team-list.sh --json --scope all; if a same-named local team has binding_state none or disconnected, stop and ask the user how to proceed. After pull succeeds, return here so the user can register a new local agent in the team that pull just created.

Read the full file on GitHub · 373 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. yesterday First seen · 373 lines · 45 tokens per session scan B da482d6b0853

Subscribe to this mod's changes

agmsg is a skill published in the GitHub repository fujibee/agmsg (1,470 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 5,384 once invoked, about $0.0002 per session on Opus 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.