codex-on-ish

codex-on-ish is a skill for Codex from OpenMinis/MinisSkills. It costs 154 tokens per session (1,070 once invoked), scanned B, original, MIT.

A setup for running the OpenAI Codex command-line program inside iSH, an Alpine Linux environment on iOS. It works around iSH networking and TLS problems with a local proxy and fixed connection settings.

In plain words
What is it for?
Use it to install and run Codex in iSH, configure the local proxy and certificates, authenticate with ChatGPT device login, and use supported model and streaming settings.
Why use it?
It addresses platform-specific failures that can prevent Codex from connecting or completing secure network handshakes on iOS. The setup also provides scripts for installation and login.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: mentions Codex.

Good fit Use it to install and run Codex in iSH, configure the local proxy and certificates, authenticate with ChatGPT device login, and use supported model and streaming settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openminis/minisskills/codex-on-ish
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.

Any agent
npx skills add OpenMinis/MinisSkills --skill codex-on-ish
Clone the repo
git clone --depth 1 https://github.com/OpenMinis/MinisSkills

Made for: Codex.

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 codex-on-ish

README.md
[![agentmods](https://agentmods.dev/badge/skills/openminis/minisskills/codex-on-ish/github.svg)](https://agentmods.dev/skills/openminis/minisskills/codex-on-ish)
Your own site
<a href="https://agentmods.dev/skills/openminis/minisskills/codex-on-ish"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/codex-on-ish/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for codex-on-ish

Your own site · 80×15
<a href="https://agentmods.dev/skills/openminis/minisskills/codex-on-ish"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/codex-on-ish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,070 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 34
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
How audits are shown
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 5.1 $0.00154 $0.01070
Opus 5 $0.00077 $0.00535
Sonnet 5 $0.00031 $0.00214
Haiku 4.5 $0.00015 $0.00107

Measured 7d ago against content hash b00686d69c4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

codex-on-ish scanned grade B with 2 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 7d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/codex-wrapper.sh, scripts/pyproxy6.py, scripts/setup.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

writes `~/.codex/config.toml` defaults (model, yolo approval policy).

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Install and run OpenAI Codex CLI inside the Minis/iSH Alpine sandbox on iOS, where rustls TLS and async sockets are broken. Covers the local MITM proxy with P-256 certs, version-spoofing to unlock newer mode
codex-on-ish/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex on iSH (Minis iOS sandbox)

Run the OpenAI Codex CLI natively in the Alpine/iSH environment. Works around the platform's broken Rust networking stack with a local MITM proxy.

Why this is needed (the two bugs)

  1. rustls misbehaves on iSH's translated CPU. Official musl binaries ≥ v0.143 panic at the first TLS handshake (installed rustls crypto provider must support ECDSA_NISTP521_SHA512) because aws-lc-rs CPU detection fails in the emulator. v0.130 (ring provider) handshakes, but ONLY with ECDSA P-256 certificates — RSA and P-521 get refused.
  2. Async sockets to remote hosts fail (connect errno 65 / reqwest error sending request). Blocking-socket clients (curl, Python) work fine; loopback connections work fine. Routing Rust traffic through a local proxy converts the hostile leg into a reliable one.

Both bugs are iSH-specific. Termux forks do NOT fix them (verified: their rustls code is identical to upstream).

Install

sh scripts/setup.sh

This downloads codex v0.130.0 musl aarch64, generates the P-256 CA/server certs, installs pyproxy6.py (proxy) and the codex wrapper into /usr/local/bin, and writes ~/.codex/config.toml defaults (model, yolo approval policy).

Login (ChatGPT account)

Codex's own login flows die within minutes (iOS kills the app at 48 CPU-s/min in background), so drive the OAuth device flow with curl instead:

sh scripts/token_poller3.sh &     # prints a live user_code, auto-renews
# user visits https://auth.openai.com/codex/device, enters the code
# poller exchanges the artifact and writes /tmp/token_result.json
sh scripts/write_auth_json.sh     # installs ~/.codex/auth.json
codex login status                # -> "Logged in using ChatGPT"

Key protocol facts (see references/auth-protocol.md):

  • POST /api/accounts/deviceauth/usercode JSON {client_id} → device_auth_id + user_code
  • poll /deviceauth/token with {device_auth_id, client_id, user_code} until it returns authorization_code + code_verifier
  • exchange at /oauth/token form-encoded (JSON is rejected) with redirect_uri=https://auth.openai.com/deviceauth/callback → id/access/refresh tokens
  • Python urllib is blocked by Cloudflare on these endpoints — always use curl.

Read the full file on GitHub · 83 lines

Files

What ships with it

8 files beside SKILL.md 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. 7d ago First seen · 83 lines · 154 tokens per session scan B b00686d69c4c

Subscribe to this mod's changes

codex-on-ish is a skill published in the GitHub repository OpenMinis/MinisSkills (410 stars, last pushed yesterday), licensed MIT. It adds 154 tokens to every session and 1,070 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories