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/antonbabenko/deliberationWrote 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/antonbabenko/deliberation/codex-login)<a href="https://agentmods.dev/commands/antonbabenko/deliberation/codex-login"><img src="https://agentmods.dev/badge/commands/antonbabenko/deliberation/codex-login/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/antonbabenko/deliberation/codex-login"><img src="https://agentmods.dev/badge/commands/antonbabenko/deliberation/codex-login.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 | $0.00050 | $0.00628 |
| Opus 5.5 | $0.00020 | $0.00251 |
| Sonnet 5.5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
codex-login 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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex login (GPT)
Starts, or joins, the ChatGPT device login for GPT on this machine and shows its link and one-time code. Nothing is asked of GPT. Use it when GPT has no login here, typically in a Claude Code web session.
Workflow
- Call the tool, with no arguments:
mcp__deliberation__codex-login({}) - Show the result's
messageto the user as-is: never paraphrased, never truncated, and never reflowed - the link and the code each stand on their own line so they are one copy. Bystatus:pending- the message carries the link and the code. Tell the user to open the link, sign in to ChatGPT, and enter the code; GPT answers from their next GPT call.authenticated- GPT has a credential here, or the login just landed through a host dialog. The message also says what to do if an existing credential turns out to be spent (a copiedauth.json): the next GPT call replaces it, orcodex logoutfirst.starting- codex has not printed its code yet. Call the tool again (it joins the same login), up to 3 times, before showing anything; only if it is stillstarting, show the message and ask the user to run/deliberation:codex-loginagain shortly.declined- only from an older server; current ones report the refusal by ending that login, and the next call offers a new code.failed/unavailable- show the message; it names the cause (no codex CLI, GPT disabled in config, a login that ended).
- Stop. Do not run shell commands, do not read or check
~/.codex/auth.json, and do not call any other deliberation tool in the same turn.
Rules
- The user's action, not an answer - the link and code are for the user to act on. Present them plainly; do not summarize them away.
- One login per session - calling this again, or calling
/ask-gptmeanwhile, joins the same login and shows the same code until it expires (15 minutes). - Never copy credentials - the login is this machine's own. Never suggest copying
auth.jsonfrom another machine: a ChatGPT refresh token works once, so a shared copy breaks on the first refresh.
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.
- 1mo ago First seen · 47 lines · 50 tokens per session scan A d29b7affdb2f
codex-login is a command published in the GitHub repository antonbabenko/deliberation (178 stars, last pushed 12d ago), licensed MIT. It adds 50 tokens to every session and 628 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-21.
Other commands, from other repositories
tldr-review
One-line TLDR PR review comments (verdict first, no filler).
quality-gate
Run the ECC quality pipeline on demand for a file or project scope.
review-artifact-comments
Works through the review comments written into a task artifact (plan or research under .ork/tasks/TASK/): lists the open ones, asks how to proceed, then replies, resolves or hands off to iterate-plan or iterate-research, and approves the artifact once nothing is open. Use when a reviewer has commented on an artifact…
review
Review a skill for quality before merge.
review
Review the current diff against project memory.
pr-manager
Comprehensive pull request management with ruv-swarm coordination for automated reviews, testing, and merge workflows.