Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bengous/claude-code-plugins/plugin install agents-bridgeWrote 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/bengous/claude-code-plugins/codex)<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/codex"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/codex/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/bengous/claude-code-plugins/codex"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/codex.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 | $0.00049 | $0.01708 |
| Opus 5.5 | $0.00020 | $0.00683 |
| Sonnet 5.5 | $0.00010 | $0.00342 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
codex scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Bridge
Every Codex call goes through codex-run.ts, which owns the invocation: a
private run directory, the resolved settings in run.json, one directory per
turn, a detached supervisor that outlives the Bash call, and resume on the same
thread with the same settings. Pass the user's request through; do not call the
codex CLI directly.
Models
<codex_models>
!"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.ts" models
</codex_models>
Without --role or -m, the run uses the codex configuration default. Pick a
role when the work calls for a tier; pass -m <slug> only when the user names
a model, with a slug from the list above.
| Work | Role |
|---|---|
| Implementation, debugging, judgment on code | coding |
| Review, audit, security, hard reasoning | audit |
| Tests, gates, research, bounded mechanical work | bounded |
--effort <level> overrides the role's effort; it must appear in that model's
efforts: list. codex-run.ts checks both against the catalog and refuses an
unknown pair with exit 2.
Run a turn
-
Create the run directory. Use the printed path literally in every later step: shell variables do not survive between Bash calls.
"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.ts" new codex -
Write the task for Codex to
<dir>/prompt.mdwith the Write tool, as an instruction addressed to Codex: the user's request verbatim, minus the parts addressed to you (which model, role or effort to use, how to report back to the user). Codex reads "ask Codex to…" as an order to run the codex CLI. The prompt never goes on the command line. -
Start the turn from the repository Codex works in (
-C <dir>otherwise):"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.ts" start <dir> --prompt-file <dir>/prompt.mdAdd
--role <role>,-m <slug>or--effort <level>as above. Add--skip-git-repo-checkonly when-Cpoints outside a git repository. Run eachcodex-run.tscommand alone, as written: a;,&&orecho $?added to it asks for permission. The envelope'sstatusalready gives the exit code.
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.
- 14d ago Changed · -40 lines · +36 tokens per session scan B → A 7cf07c241351
- 1mo ago Changed · +8 lines e5ad14a5f10d
- 1mo ago First seen · 187 lines · 13 tokens per session scan B 1f93b8f11d49
codex is a skill published in the GitHub repository bengous/claude-code-plugins (5 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,708 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 2026-08-31.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.
tencent-docs
A Tencent Docs assistant for creating, reading, editing, organizing, importing, and exporting online documents, spreadsheets, presentations, diagrams, and forms.
wechat-search
Search WeChat Official Account articles using OpenClaw's web search, Tavily API, and web fetch capabilities with compliance-focused design.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.