oat-postcard

A plugin marketplace listing for Postcard, a tool for sending asynchronous one-to-one messages between AI-agent sessions using a Git-backed record. It includes a command-line tool, commands, a skill, a helper agent for sorting incoming messages, and session hooks.

In plain words
What is it for?
Listing and distributing the Postcard plugin, documenting its version and repository, and supporting message exchange, inbox sorting, and session-based agent workflows.
Why use it?
It describes how separate agent sessions can exchange messages and track them in a shared Git-based record, which helps coordinate work that does not happen at the same time.

Plugin 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.

Claude Code
/plugin marketplace add Open-Agent-Tools/Postcard
agentmods
npx agentmods add plugins/open-agent-tools/postcard/marketplace
Clone the repo
git clone --depth 1 https://github.com/Open-Agent-Tools/Postcard

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

oat-postcard 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 2d ago.

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-plugin/marketplace.json · 22 lines

What it actually says

{
  "name": "oat-postcard",
  "owner": {
    "name": "Open Agent Tools"
  },
  "metadata": {
    "description": "Asynchronous 1-to-1 postcard messaging between AI agent sessions via a Git-backed ledger",
    "version": "0.4.1"
  },
  "plugins": [
    {
      "name": "postcard",
      "source": "./",
      "description": "Postcard protocol for cross-session AI agent messaging. Ships a CLI, slash commands, a model-invoked skill, a Clerk subagent for inbox triage, and SessionStart / Stop / UserPromptSubmit hooks.",
      "version": "0.4.1",
      "license": "MIT",
      "repository": "https://github.com/Open-Agent-Tools/Postcard",
      "keywords": ["messaging", "agents", "ledger", "git", "async", "multi-agent"]
    }
  ]
}
Files

What ships with it

1 file beside marketplace.json 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. 2d ago First seen · 22 lines scan A 18ed1968bd91

Subscribe to this mod's changes

oat-postcard is a plugin published in the GitHub repository Open-Agent-Tools/Postcard (2 stars, last pushed 22d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.