codexhub AGENTS.md

Contributor instructions for CodexHub, a project that catalogs coding-agent add-ons. They require catalog data to be evidence-backed and builds to be checked offline.

In plain words
What is it for?
Updating catalog data, preserving reproducibility, checking tests and offline builds, and formatting text and links correctly.
Why use it?
They set rules for reliable catalog entries, safe handling of indexed projects, permitted links, and pre-pull-request checks.

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/zpf2234/codexhub/agents-md
Clone the repo
git clone --depth 1 https://github.com/zpf2234/codexhub

Made for: Codex, OpenCode.

Per session 92 This file is loaded in full into every session.
When invoked 92 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 $0.00092 $0.00092
Opus 5 $0.00046 $0.00046
Sonnet 5 $0.00018 $0.00018
Haiku 4.5 $0.00009 $0.00009

Measured 2d ago against content hash 37cdd06b5dfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codexhub 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 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.

AGENTS.md · 10 lines

What it actually says

CodexHub contributor guide

Project expectations

  • Keep catalog data evidence-backed and reproducible.
  • Never clone, install, execute, or connect to an indexed project.
  • Run npm test and npm run build:offline before opening a pull request.
  • Treat stars and forks as popularity signals, never as quality evidence.
  • Render catalog text as text, not HTML, and allow only http/https links.
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 · 10 lines · 92 tokens per session scan A 37cdd06b5dfb

Subscribe to this mod's changes

codexhub AGENTS.md is an instructions file published in the GitHub repository zpf2234/codexhub (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session, about $0.0005 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.