What is codex-claude-pipeline?

A workflow for coordinating Codex and Claude across planning, implementation, review, and limited revision stages. It keeps a shared run record containing the goal, constraints, files, decisions, checks, and result references.

Use it for implementation tasks that need one agent to write code and another to plan, independently review it, and make a bounded follow-up change.

It gives cross-agent work explicit handoffs and phase boundaries instead of repeating work or passing large conversation transcripts around. It also controls when failed stages may be retried.

codex-claude-pipeline — Skill for Codex by maximyz3d/relaybridge

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 maximyz3d/relaybridge --skill codex-claude-pipeline

Clone the repo

git clone --depth 1 https://github.com/maximyz3d/relaybridge

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/maximyz3d/relaybridge/codex-claude-pipeline/github.svg)](https://agentmods.dev/skills/maximyz3d/relaybridge/codex-claude-pipeline)

Your own site

<a href="https://agentmods.dev/skills/maximyz3d/relaybridge/codex-claude-pipeline"><img src="https://agentmods.dev/badge/skills/maximyz3d/relaybridge/codex-claude-pipeline/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/maximyz3d/relaybridge/codex-claude-pipeline"><img src="https://agentmods.dev/badge/skills/maximyz3d/relaybridge/codex-claude-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,557 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	$0.00033	$0.01557
Opus 5.5	$0.00013	$0.00623
Sonnet 5.5	$0.00007	$0.00311
Haiku 4.5	$0.00003	$0.00156

Measured 1mo ago against content hash 9ce0ce125b27, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-claude-pipeline 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.

skills/codex-claude-pipeline/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex-Claude Pipeline

Use Codex as the orchestrator and primary writer. Use Claude for an independent plan, a fresh post-implementation review, and one bounded revision per accepted review cycle when changes are required.

Invariants

Honor explicit user provider restrictions before the default roles below. For a Codex-only Astra/ultra run, use the existing creation tool with profile:"codex-astra-ultra" and verify that exact persisted profile in its response. Read-only planning and both reviews then use Codex/Astra/ultra; there is no Claude fallback. Claim revisions with claim_pipeline_revision, preserve the token, and report corrections with complete_pipeline_revision. The fresh final review still gates completion. Missing profile support is a runtime limitation, not permission to invoke a prohibited provider. Record actual reviewer identity; never manufacture a Claude verdict.
Keep one canonical run packet with the objective, constraints, non-goals, scoped files, base revision, decisions, acceptance checks, and artifact IDs.
Give every delegated lane one bounded question and one output contract. Return summaries and evidence, never whole transcripts or large file bodies.
Check active runs before dispatch. Do not repeat work already in progress or rerun a completed phase merely to recover context; read its receipt/artifact.
Let the bridge handle its bounded durable backoff for typed transient planning/review failures. Read state with get_pipeline, then invoke reconcile_pipeline only when named in nextActions; do not create a replacement. Use retry_failed_pipeline_provider only for an older terminal run whose durable task record proves a transient read-only failure. Never replay a failed writer automatically. For a bridge-interrupted read-only task, first confirm the former provider process is no longer alive; polling alone must not launch its replacement.
Fan out only independent read-only discovery. Never fan out writers.
Use the browser_researcher or open_in_chrome only when live UI, console, network, screenshot, or browser-only evidence is required. Keep Chrome evidence bounded; do not transfer raw DOM or full network bodies. The default slim Chrome MCP supplies navigation, evaluation, and screenshots. Console, network, or performance work requires the operator to rerun ./install-chrome-mcp.sh --full-tools --full-permissions and restart clients.
Maintain one writer lease containing owner, file scope, and base revision. Codex normally owns it. Release it before the Claude reviser can acquire it.
Start planning and review in fresh, non-persistent Claude sessions. Do not let implementation conversation or earlier conclusions anchor the reviewer.
Compact a continuing coordination thread near 60–70% context use. Preserve only decisions, file scope, artifact IDs, risks, and verification state. Start a fresh phase session instead of compacting a completed phase into the next.

Read the full file on GitHub · 118 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 302 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.

1mo ago Changed · +7 lines 9ce0ce125b27
1mo ago Changed · +10 lines 58dbacbe867a
1mo ago First seen · 101 lines · 33 tokens per session scan A 26227d181960

Subscribe to this mod's changes

codex-claude-pipeline is a skill published in the GitHub repository maximyz3d/relaybridge (0 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,557 once invoked, about $0.0001 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 2026-09-05.

Building agents Planning

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.