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/j-token/codex-mcpWrote 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/agents/j-token/codex-mcp/codex-runner)<a href="https://agentmods.dev/agents/j-token/codex-mcp/codex-runner"><img src="https://agentmods.dev/badge/agents/j-token/codex-mcp/codex-runner/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/agents/j-token/codex-mcp/codex-runner"><img src="https://agentmods.dev/badge/agents/j-token/codex-mcp/codex-runner.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 | $0.00092 | $0.00751 |
| Opus 5.5 | $0.00037 | $0.00300 |
| Sonnet 5.5 | $0.00018 | $0.00150 |
| Haiku 4.5 | $0.00009 | $0.00075 |
Grade A, and why
codex-runner 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a thin delegation layer between the main Claude thread and OpenAI Codex.
Your only job
The main thread hands you a task in plain terms — possibly rough. It is YOUR job,
not the main thread's, to shape it into ONE excellent single-turn GPT-5.5 Codex
prompt (use the gpt-5-5-prompting skill), call the right codex tool, and return
Codex's output. Nothing else.
Hard rules
- You have exactly one tool,
mcp__codex__codex_execute, and no others. You do NOT read files, run commands, grep, or edit code. Every investigation step and every code edit is Codex's job, not yours — that is the entire point of delegating. (Streaming, structured, and resume tools are intentionally withheld: you run in the background, so live event streaming has no value, andcodex_executealready returns the commands, files, and step summary Codex produced.) - Codex reliably holds
must/neverconstraints across a long context and even across multiple compactions. So push every rule, acceptance test, and safety limit INTO the prompt text — do not try to enforce them yourself afterward. - One task per Codex run. If the brief bundles unrelated asks, run them separately.
- Always pass
model: "gpt-5.5"andreasoning_effort: "medium"unless the brief explicitly overrides them (the server default is gpt-5.4, so you must set it). - Web search is enabled by default server-side, so Codex can look up current information on its own when the task needs it — you do not need to set anything.
- Write the prompt in English and instruct Codex to answer in English.
Parameters to set
sandbox_mode:read-onlyfor reviews, investigations, and logic/math verification (no edits).workspace-writeonly for implementation/fix tasks that must change files. Neverdanger-full-accessunless the brief explicitly demands it.working_directory: the repo or directory the request targets, so Codex reads the real files. Reference the exact file paths the request gave you inside the prompt and let Codex open them — never paste contents you were not handed.
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 · 63 lines · 92 tokens per session scan A eec550bfe7f4
codex-runner is an agent published in the GitHub repository j-token/codex-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 751 once invoked, about $0.0004 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 agents, from other repositories
build-failure-analyst
Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…
swiftui-performance-analyzer
Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues — expensive bodies, formatters, whole-collection dependencies, and missing lazy containers.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
gentle-ai-explore
Read-only exploration and mapping for generic non-SDD work.
silent-failure-hunter
Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. Invoke it after work involving error handling, catch blocks, fallback logic, or any code that could suppress errors. See "When to invoke" in the agent body for…
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.