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.
git clone --depth 1 https://github.com/hamza-ali-shahjahan/claudexWrote 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/commands/hamza-ali-shahjahan/claudex/debate)<a href="https://agentmods.dev/commands/hamza-ali-shahjahan/claudex/debate"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/claudex/debate/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/commands/hamza-ali-shahjahan/claudex/debate"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/claudex/debate.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00018 | $0.01486 |
| Opus 5 | $0.00009 | $0.00743 |
| Sonnet 5 | $0.00004 | $0.00297 |
| Haiku 4.5 | $0.00002 | $0.00149 |
Grade A, and why
debate 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 10d 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.
This is a copy
100% identical to debate — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running ClauDex debate — a structured argument between Claude Code (you, 🧡) and OpenAI Codex (🖤) over a real design decision. Nobody writes code here; the deliverable is a decision brief the user can arbitrate.
Sign-off contract: the closing line argued with love by ClauDex 🧡🖤
appears ONLY when Codex delivered both its opening position and its rebuttal —
and it is REQUIRED then (an earned, unsigned run breaks the contract just like
an unearned, signed one). Refusal, interruption, or an empty motion all end
UNSIGNED. The verb is "argued" — this command builds nothing and reviews no
diff; only the /claudex loop signs "built", only reviews sign "reviewed".
Preflight — it takes two to ClauDex
-
Run
codex --versionand check auth (codex login statusor the equivalent for the installed version). If either fails, STOP before any framing or arguing and reply with exactly:It takes two to ClauDex. 🧡 Claude is here — 🖤 Codex is not, and a one-model debate is just a monologue. Fix it in two lines, then come back for the argument:
npm i -g @openai/codex codex login -
The motion. "$ARGUMENTS" must state a decision. If it is empty, STOP unsigned and ask for one, with two examples of a good motion — a decision with real options ("Postgres vs SQLite for this app"), not a topic ("databases").
(No git preflight — a debate needs a question, not a diff. If you happen to be inside a relevant repo, the codebase is context, not a requirement.)
The debate
- Frame the motion. Sharpen "$ARGUMENTS" into a decision question with 2–3 concrete options. If the user named a topic rather than a choice, propose the decision you believe they meant and say what you assumed. Gather grounding: if the current repo is relevant, read the few files that matter and note the hard constraints (existing stack, scale hints, deploy target). Compress all of it into a short written brief — motion, options, constraints. Keep it under a page; a debate is not a survey.
- Claude's opening (yours). Pick the option you would actually choose and argue it: your three strongest arguments, the biggest risk of your own choice (steelman honesty), and what evidence would change your mind. Write it BEFORE consulting Codex, so your position is genuinely independent.
- Codex's opening — safe transport. Write the brief from step 1 to a
temp file (e.g.
$TMPDIR/claudex-debate.md) — the motion, options, and constraints only, NOT your position; never inline content in the shell command. Then, with a hard timeout of ~10 minutes:
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.
- 10d ago First seen · 111 lines · 18 tokens per session scan A d735ae5d4c05
debate is a command published in the GitHub repository hamza-ali-shahjahan/claudex (4 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,486 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to debate, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
duck-off
Turn off Rubber Duck mode and answer normally.
save
Save the current session digest. Fans out across every writable memory tier per the house-map. Tier 0 always; Tier 1 if reachable; Tier 2 only if registered writable with auth. Each tier independent — failures degrade gracefully.
notice
Maude surfaces patterns from the turn-by-turn trace — recurring topics, repeated mistakes, time-of-day patterns, sessions that keep ending in the same place.
check-on-claude
Maude checks on Claude — repeated tool calls, unread context, confabulation risk, missed CLAUDE.md, the patterns Claude doesn't see in himself.
promote
Show what the tape is holding for your word, and promote the ones you approve into canon. Agent inference never becomes canon on its own — this is the door, and your hand is on it.
help
Rubber Duck: what it does, how to steer it, how to stop it.