A guided command for setting up oat-postcard, a text-only messaging system between AI coding-agent sessions on the same machine. It saves a coordination note in the project and shows the current session and other online sessions.

Use it to initialize the project hint, see session addresses, check who is online, and learn how to send or receive postcards.

It helps separate agent sessions share context and coordinate work without relying on memory or direct interaction.

onboard — Command by Open-Agent-Tools

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 commands/open-agent-tools/postcard/onboard

Clone the repo

git clone --depth 1 https://github.com/Open-Agent-Tools/Postcard

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 372 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.

Model	Per session	Once invoked
Fable 5	$0.00026	$0.00372
Opus 5	$0.00013	$0.00186
Sonnet 5	$0.00005	$0.00074
Haiku 4.5	$0.00003	$0.00037

Measured 2d ago against content hash 1a98096f653b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboard 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.

commands/onboard.md · 32 lines

What it actually says

Guide the user through oat-postcard in this order. Keep the whole response tight — roughly a screenful, no more.

What it is (one short paragraph): asynchronous 1-to-1 messaging between AI agent sessions on this machine. Fire-and-forget, text-only, backed by a git ledger. Handy when another session has context you'd otherwise have to guess — cross-tier specs, shared schemas, "ask the other agent" handoffs.
Persist the hint. Run oat-postcard init to append an idempotent coordination block to this project's CLAUDE.md (or AGENTS.md if that's what the project uses). Show the one-line result. If it reports "already present", note that and move on.
Show current state. Run oat-postcard whoami and oat-postcard directory and report both inline. If no other sessions are listed, tell the user they can start a second Claude Code session in any other project and re-run /postcard:directory to see it appear.
How to use (two one-liners):
- Send: /postcard:send <address> "<title>" "<body>" (title ≤140 chars, body ≤1400).
- Receive: the postcard-reader subagent triages automatically — routine items go to TODO.md, urgent ones surface inline in your next reply.

Do not paste in the README or re-explain topics you've already covered.

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.

2d ago First seen · 32 lines · 26 tokens per session scan A 1a98096f653b

Subscribe to this mod's changes

onboard is a command published in the GitHub repository Open-Agent-Tools/Postcard (2 stars, last pushed 23d ago), licensed MIT. It adds 26 tokens to every session and 372 once invoked, about $0.0001 per session on Opus 5. 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.

Building agents agents claude-code claude-code-plugin cli ipc messaging

template

Manage issue templates for streamlined issue creation.

gastownhall/beads · 0 tokens

cross-validate

Take a specific scientific claim and confirm or refute it across 3+ independent databases, then report concordance. Use before publishing, citing, or acting on a fact when you want to know how strongly it's supported. Forces multi-source verification that the agent doesn't naturally enforce.

mims-harvard/ToolUniverse · 59 tokens

translate-id

Resolve an identifier across all relevant namespaces (HGNC symbol, Ensembl, UniProt, NCBI Gene ID, RefSeq, MGI, OMIM, ChEMBL, PubChem, etc.). Detects the input namespace automatically, picks the right resolver tool, and returns a complete cross-reference table. Use when you have an ID in one namespace and need it in…

mims-harvard/ToolUniverse · 85 tokens

onboard