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.
npx skills add OpenMinis/MinisSkills --skill codex-on-ishgit clone --depth 1 https://github.com/OpenMinis/MinisSkillsWrote 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.
[](https://agentmods.dev/skills/openminis/minisskills/codex-on-ish)<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.
<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>- NVIDIA SkillSpector warn
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
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 5.1 | $0.00154 | $0.01070 |
| Opus 5 | $0.00077 | $0.00535 |
| Sonnet 5 | $0.00031 | $0.00214 |
| Haiku 4.5 | $0.00015 | $0.00107 |
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.
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 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)
- 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. - Async sockets to remote hosts fail (
connect errno 65/ reqwesterror 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/usercodeJSON{client_id}→ device_auth_id + user_code- poll
/deviceauth/tokenwith{device_auth_id, client_id, user_code}until it returnsauthorization_code+code_verifier - exchange at
/oauth/tokenform-encoded (JSON is rejected) withredirect_uri=https://auth.openai.com/deviceauth/callback→ id/access/refresh tokens - Python urllib is blocked by Cloudflare on these endpoints — always use curl.
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.
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.
- 7d ago First seen · 83 lines · 154 tokens per session scan B b00686d69c4c
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.