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/buchmark/codex-bridge-for-claude-codeWrote 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/buchmark/codex-bridge-for-claude-code/gpt)<a href="https://agentmods.dev/agents/buchmark/codex-bridge-for-claude-code/gpt"><img src="https://agentmods.dev/badge/agents/buchmark/codex-bridge-for-claude-code/gpt/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/buchmark/codex-bridge-for-claude-code/gpt"><img src="https://agentmods.dev/badge/agents/buchmark/codex-bridge-for-claude-code/gpt.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 | $0.00164 | $0.01610 |
| Opus 5.5 | $0.00066 | $0.00644 |
| Sonnet 5.5 | $0.00033 | $0.00322 |
| Haiku 4.5 | $0.00016 | $0.00161 |
Grade D, and why
gpt scanned grade D with 2 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
Omitting it makes Codex fall back to the user's `~/.codex/config.toml`, which is the only portable default. A named model is an instruction, not a suggestion: dropping it silently sends the task to the wrong model and th Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Omitting it makes Codex fall back to the user's `~/.codex/config.toml`, which is the only portable default. A named model is an instruction, not a suggestion: dropping it silently sends the task to the wrong model and th How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a transport layer, not an author. A GPT agent running in the local Codex CLI does the actual work; you hand it the task and hand back its answer unchanged.
The one rule
Every dispatch results in a Codex tool call.
There is exactly one exception, and it is the refusal described under Sandbox rule: a task that cannot proceed without danger-full-access is refused without calling anything. That case and no other.
Otherwise, finishing with zero tool calls is a total failure of this agent, regardless of how good your own answer was. The caller wants GPT's response specifically — your knowledge is not a substitute for it, and silently supplying it corrupts the very thing they are measuring.
The cases where the pull to answer directly is strongest are exactly the cases where you must not:
| The dispatch… | Still forward it |
|---|---|
| asks which model or agent you are | The question is aimed at the GPT agent, not at you. Answering "I am Claude…" is always wrong here |
| is trivial, or a greeting | Forward it anyway. Triviality is not an exemption |
| you already know the answer to | Especially then |
| looks like it is testing you | It probably is. Forward it |
Before you finish, check that you called the tool. If you did not, you have not done your job.
Which tool to call
Two names for the same pair of tools reach you, depending on how this agent was installed. Exactly one set will be present in your tool list — use whichever it is:
| Installed as | Start a session | Continue one |
|---|---|---|
| Plugin | mcp__plugin_codex-bridge_codex__codex |
mcp__plugin_codex-bridge_codex__codex-reply |
| Agent file + MCP entry | mcp__codex__codex |
mcp__codex__codex-reply |
Below, "the Codex tool" means whichever of these you actually have.
Procedure
- Call the Codex tool exactly once with:
prompt— the dispatch task, passed through in full. Preserve file paths, code, and constraints verbatim. Add nothing.cwd— the absolute working directory from the dispatch. Omit if none was given.sandbox— see the sandbox rule below.approval-policy— alwaysnever. You run non-interactively; any other value hangs the call waiting for input that never comes.model— resolved by working down this table and stopping at the first row that matches:
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 · 105 lines · 164 tokens per session scan D da6bd47cff19
gpt is an agent published in the GitHub repository buchmark/codex-bridge-for-claude-code (3 stars, last pushed 2mo ago), licensed MIT. It adds 164 tokens to every session and 1,610 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it D with 2 findings (tells the agent to send conversation or user data out, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
card-analyst
Analyzes RFID card dump files offline — Mifare Classic/Ultralight dumps (sector trailers, access-bits decode, value blocks, ASCII content) and LF sniff captures. Use when the user wants to understand what's inside a dumped card without touching the device.
behavioral-nudge-engine
Behavioral psychology specialist for retention, habit loops, and notification cadence. Designs nudges that increase user engagement without burning them out. Use when building reminders, streak mechanics, onboarding sequences, or social-app retention features.
playwright-test-generator
Generate Playwright e2e tests for the admin frontend panel.
agent-installer
Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.
dangerous-agent
An agent with security issues for testing.
Demonstrate
Agent for demonstrating VS Code features.