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 commands/gitguffaw/codex-router/cligit clone --depth 1 https://github.com/gitguffaw/codex-routerWhat 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 | $0.00013 | $0.00279 |
| Opus 5 | $0.00006 | $0.00139 |
| Sonnet 5 | $0.00003 | $0.00056 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
cli 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 yesterday.
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.
What it actually says
Run a raw Codex CLI command through the shared companion runtime.
Raw slash-command arguments:
$ARGUMENTS
Use this for Codex features that are not first-class codex-router commands, such as:
--helpand<command> --helpto inspect the installed CLI's current flagsfeatures listmcp listplugin listdoctorcloud status <task-id>resume <session-id>
Do not rely on a copied Router list of raw Codex flags. Use the installed CLI help so newly added commands and options are visible without a Router release.
Do not use this command for normal delegated analyze/exec/review/rescue work when a first-class /codex-router:* command exists.
Do not launch a bare interactive Codex TUI unless the user explicitly asks for it and understands it may not return cleanly through Claude Code's command runner.
Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" cli "$ARGUMENTS"
Return stdout and stderr verbatim, exactly as-is.
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.
- yesterday First seen · 34 lines · 13 tokens per session scan A 288457345400
cli is a command published in the GitHub repository gitguffaw/codex-router (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 13 tokens to every session and 279 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
release
Prepare a new release for sandvault. This command updates the changelog, bumps the version, and creates a PR.
verify
Run the full verification pipeline before committing.
codex-review-waive
Waive a disputed Codex review finding so it stops blocking commits.
review
Review the current plan with peer LLMs via inspectrum.
codex-review
Run a Codex code review on commits, branches, or uncommitted changes.
cancel
Cancel an active background Codex job in this repository.