postern AGENTS.md

Repository instructions for setting up Postern, a product documented through a step-by-step setup contract. They tell an AI agent which guide to follow, when to stop for the user, and where to find development documentation.

In plain words
What is it for?
Use them when installing or changing Postern, especially to follow the setup contract, handle user approval points, or consult the contributing and agent guides.
Why use it?
They prevent an agent from improvising setup steps or using an outdated procedure.

Instructions file for CodexOpenCode

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 instructions/getpostern/postern/agents-md
Clone the repo
git clone --depth 1 https://github.com/getpostern/postern

Made for: Codex, OpenCode.

Per session 203 This file is loaded in full into every session.
When invoked 203 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00203 $0.00203
Opus 5 $0.00102 $0.00102
Sonnet 5 $0.00041 $0.00041
Haiku 4.5 $0.00020 $0.00020

Measured yesterday against content hash 571f1ebcd037, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

postern AGENTS.md 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 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.

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.

AGENTS.md · 8 lines

What it actually says

AGENTS.md — superseded by the setup contract

Audience: an agent setting up Postern on behalf of the person who owns the box. This file's old step list and route tables are retired. The replacement is a fuller contract, verified end to end on a clean machine by a first-time user's agent:

Read setup-with-your-agent.md and follow it. It carries the phases in order, every HUMAN stop, the exact routes with body shapes, the never-do-these rules, and the troubleshooting table. Do not improvise a setup path from this file or from the API's shape — that contract exists so you do not have to.

If you are here to change the code instead, read CONTRIBUTING.md and CLAUDE.md. The person-facing, screen-by-screen documentation — and the API reference — is at https://docs.getpostern.com.

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 · 8 lines · 203 tokens per session scan A 571f1ebcd037

Subscribe to this mod's changes

postern AGENTS.md is an instructions file published in the GitHub repository getpostern/postern (1 stars, last pushed 22d ago), licensed Apache-2.0. It adds 203 tokens to every session, about $0.0010 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.