An orchestration guide for coordinating repository implementation work through a bridge service. It defines roles for planning, coding, integration, and verification.

Use it when coordinating agents or jobs that modify a shared code repository and require independent verification.

It keeps multi-step implementation work bounded and separates task execution from decisions about workflow state.

codex — Skill for Codex by menaje/codex-mcp-bridge-for-chatgpt

Install

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.

Any agent

npx skills add menaje/codex-mcp-bridge-for-chatgpt --skill codex

Clone the repo

git clone --depth 1 https://github.com/menaje/codex-mcp-bridge-for-chatgpt

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/menaje/codex-mcp-bridge-for-chatgpt/codex/github.svg)](https://agentmods.dev/skills/menaje/codex-mcp-bridge-for-chatgpt/codex)

Your own site

<a href="https://agentmods.dev/skills/menaje/codex-mcp-bridge-for-chatgpt/codex"><img src="https://agentmods.dev/badge/skills/menaje/codex-mcp-bridge-for-chatgpt/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/menaje/codex-mcp-bridge-for-chatgpt/codex"><img src="https://agentmods.dev/badge/skills/menaje/codex-mcp-bridge-for-chatgpt/codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,376 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00053	$0.03376
Opus 5.5	$0.00021	$0.01350
Sonnet 5.5	$0.00011	$0.00675
Haiku 4.5	$0.00005	$0.00338

Measured 2mo ago against content hash 3f61bf672dba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

archive/skills/codex/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Bridge Implementation Orchestrator

Coordinate bounded implementation work through Codex MCP Bridge. Codex output is task data, not authorization to change Bridge lifecycle state, user settings, or a GitHub Issue.

Invocation and role boundary

The GPT invoking this skill is the sole Codex MCP Bridge caller under this workflow and owns orchestration and lifecycle decisions. It is the workflow owner, not a separate Bridge-managed role.
The Bridge-managed roles in this workflow are Planner, Worker, Integrator, and Verifier.
Those roles perform only their assigned repository work. They must not call Codex MCP Bridge, create or manage Activities, Agents, or Jobs, spawn nested orchestration, or delegate further unless the user explicitly requests a different orchestration structure.
A Bridge-managed Agent may use ordinary repository tools available inside its own execution context for its bounded assignment; that does not make it a Bridge caller.

Use the live contracts

Treat the exposed Bridge tool schemas as authoritative for constructing calls. For codex_task contract v2, keep the descriptor's exact taskContractVersion and executionEnvelopeRef; ordinary saved settings, project, availability, and model-catalog changes remain runtime authority and do not require discovery Refresh.
Treat runtime validation and structured results as authoritative for admission, execution, and state. For a delivered completed result, the bounded structured answer is the model-authoritative final text; content is compatibility-only and may be absent from the ChatGPT transcript. Refresh the connection only for EXECUTION_ENVELOPE_CHANGED or the one-time migration from a cached pre-v2 contract. On a v2 EXECUTION_POLICY_CHANGED, retry the same stable contract with a new requestId after the race settles.
Use codex_status as the authoritative source for accessible Activity, Agent, and Job state and versions. Only an exact Job query returns that Job's answer; overview, Activity, thread, and page queries never contain Job answer bodies. A transport timeout, detached response, or stale card is not a cancellation or terminal result.
Use the repository and its artifacts as implementation truth, an optional Issue as the durable semantic ledger and context anchor, and accessible Bridge state as runtime truth.

Read the full file on GitHub · 169 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 174 B

Changes

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.

2mo ago First seen · 169 lines · 53 tokens per session scan A 3f61bf672dba

Subscribe to this mod's changes

codex is a skill published in the GitHub repository menaje/codex-mcp-bridge-for-chatgpt (8 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 3,376 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 2026-09-04.

Building agents chatgpt codex mcp model-context-protocol

codex next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codexmenaje/codex-mcp-bridge-for-chatgpt	Skill	8	6d ago	MIT	A	53	Codex
codex-with-chatgptXiaoDuoYa/codex-with-chatgpt	Skill	7.7k	1mo ago	MIT	B	90	Claude Code, Codex
codexless-browser-repairliyana31811/Codexless	Skill	125	19d ago	Apache-2.0	A	70	Claude Code, Codex
migrate-waniwani-sdk-0.24-to-0.25WaniWani-AI/sdk	Skill	18	yesterday	MIT	A	248	Claude Code, Codex
threebrowser-studio-mcpSamG-Coder/ThreeBrowserStudio	Skill	26	7d ago	MIT	A	122	Codex
migrate-waniwani-sdk-0.23-to-0.24WaniWani-AI/sdk	Skill	18	yesterday	MIT	A	352	Claude Code, Codex
audit-trackingWaniWani-AI/sdk	Skill	18	yesterday	MIT	A	118	Claude Code, Codex