Cloister AGENTS.md

Cloister AGENTS.md is an instructions file for Codex, OpenCode from yi427/Cloister. It costs 268 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Cloister, a security-boundary product focused on running work in Apple containers on macOS.

In plain words
What is it for?
Use them when changing Cloister: follow its profile contract, separate command construction from presentation, keep tests and fixtures in the expected locations, and run its formatting and verification commands.
Why use it?
They keep security assumptions explicit and prevent unsafe claims or hidden access to host credentials, privileged sockets, networks, or workspace files.

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/yi427/cloister/agents-md
Clone the repo
git clone --depth 1 https://github.com/yi427/Cloister

Made for: Codex, OpenCode.

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 Cloister AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yi427/cloister/agents-md.svg)](https://agentmods.dev/instructions/yi427/cloister/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/yi427/cloister/agents-md"><img src="https://agentmods.dev/badge/instructions/yi427/cloister/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 268 This file is loaded in full into every session.
When invoked 268 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 $0.00268 $0.00268
Opus 5 $0.00134 $0.00134
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured 3d ago against content hash eae13dacdf25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Cloister 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 3d 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.

AGENTS.md · 29 lines

What it actually says

Repository guidance

Cloister is a security-boundary product. Prefer explicit, inspectable behavior over hidden defaults.

Scope

  • Keep the first product terminal-first and macOS/Apple-container focused.
  • Treat the profile schema as a public contract and version it.
  • Keep Apple container command construction separate from CLI presentation.
  • Never silently mount host credential directories or privileged sockets.
  • Never claim that a bind-mounted workspace is protected from writes made by the guest.
  • Never equate a named container network with blocked internet access.

Workflow

  • Keep changes small and reviewable in Git.
  • Do not commit local profiles, credentials, runtime state, or agent transcripts.
  • Keep focused module tests beside their Rust modules and put public-behavior, cross-module, and CLI tests under tests/.
  • Store deterministic test data under tests/fixtures/; never use real credentials, home-directory state, or machine-specific absolute paths there.
  • Run make format after editing Rust code and make verify before considering a change complete.
  • Keep .githooks/pre-commit aligned with make verify; the hook must validate the staged snapshot without modifying or staging the working tree.
  • Add focused tests when profile parsing or command construction is introduced.
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. 3d ago First seen · 29 lines · 268 tokens per session scan A eae13dacdf25

Subscribe to this mod's changes

Cloister AGENTS.md is an instructions file published in the GitHub repository yi427/Cloister (2 stars, last pushed 22d ago), licensed Apache-2.0. It adds 268 tokens to every session, about $0.0013 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.