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 agentmods add skills/sonichi/sutando/claude-codexnpx skills add sonichi/sutando --skill claude-codexgit clone --depth 1 https://github.com/sonichi/sutandoWrote 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/sonichi/sutando/claude-codex)<a href="https://agentmods.dev/skills/sonichi/sutando/claude-codex"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/claude-codex.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00081 | $0.01769 |
| Opus 5 | $0.00041 | $0.00885 |
| Sonnet 5 | $0.00016 | $0.00354 |
| Haiku 4.5 | $0.00008 | $0.00177 |
Grade A, and why
claude-codex 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Codex
Delegate work from Claude Code to the local codex CLI. This skill assumes Codex is already authenticated on this machine. It does not mint, extract, or transfer credentials.
Usage: /claude-codex [prompt]
ARGUMENTS: $ARGUMENTS
When to Use
- "Ask Codex to review this change"
- "Use my Codex subscription from Claude Code"
- Need a second model to inspect a bug, review a diff, or propose an implementation
- Need a Codex result saved or streamed from the current repo
- Spec-driven one-shot build of a self-contained artifact (HTML/CSS/JS prototype, single-file
demo) — use
--goalto invoke Codex's/goalmode
When NOT to Use
- Interactive review from this Claude Code session → use
/codex:review,/codex:adversarial-review, or/codex:rescuefrom the openai/codex-plugin-cc plugin. They're the discoverable, versioned path. - Anything that needs a Codex session ID / job tracking / status polling → plugin's
/codex:statusis the right surface.
If you don't see /codex:* slash-commands available, install the plugin in this Claude Code session:
/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/reload-plugins
/codex:setup
This skill stays as the non-interactive bash-wrapper path — invoked by discord-bridge.py's team-tier ===SUTANDO SYSTEM INSTRUCTIONS=== block (codex exec --sandbox read-only on Discord tasks from non-owner senders), cron-fired jobs that need a one-shot codex call, and similar file-bridge workflows where a plugin slash-command can't reach.
Guardrails
- Prefer
codex review --uncommittedfor code review. - Prefer
codex execfor analysis, planning, or implementation prompts. - Keep Codex pointed at the same repo with
-C "$PWD"unless the user asked for another directory. - Default to
workspace-writesandbox or stricter. Do not use bypass flags unless the user explicitly asks.
Quick Checks
codex login status
bash "$SKILL_DIR/scripts/codex-run.sh" --check
What ships with it
4 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.
- 4d ago First seen · 145 lines · 81 tokens per session scan A 65701060c000
claude-codex is a skill published in the GitHub repository sonichi/sutando (391 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,769 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
contacts
Manage contacts, communication channels, access control, and invite links.
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…
assistant-migration
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…
guardian-verify-setup
Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.
media-processing
Ingest and process media files (video, audio, image).