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.
npx skills add DannyMac180/skills --skill codex-relaygit clone --depth 1 https://github.com/DannyMac180/skillsWrote 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/dannymac180/skills/codex-relay)<a href="https://agentmods.dev/skills/dannymac180/skills/codex-relay"><img src="https://agentmods.dev/badge/skills/dannymac180/skills/codex-relay/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/dannymac180/skills/codex-relay"><img src="https://agentmods.dev/badge/skills/dannymac180/skills/codex-relay.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 | $0.00058 | $0.00759 |
| Opus 5.5 | $0.00023 | $0.00304 |
| Sonnet 5.5 | $0.00012 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
codex-relay 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Relay
Open one native Codex task, hand off a bounded job, end this turn, and verify the worker's callback. The invocation plus a request to open a task is the authorization; never create tasks otherwise.
Preconditions
If any is missing, explain and stop. Do not create an orphan, promise a wake-up you cannot deliver, or substitute a CLI, subagent, or automation.
create_threadandsend_message_to_threadare exposed.CODEX_THREAD_IDis non-empty (plus host if remote). Never derive it from the cwd or reuse a child ID.- The user named the task.
Model and effort
Use exactly what the user selected, handling the two independently: omit only the model field if no model was named, and only the thinking field if no effort was named, so each falls back to the configured default. If a model is unavailable, say so and ask; never substitute. Resolve ambiguity from tool metadata; ask only when material.
Workspace
Use list_projects to find the target when files are involved. Honor a user-specified branch, working-tree state, or saved checkout via the option create_thread supports; only when unspecified, default to a worktree for Git projects and local otherwise. A default worktree starts from the default branch without uncommitted changes; if a requested state is unsupported, say so rather than implying it was included. For projectless work, reference supplied accessible files.
Handoff brief
The worker inherits nothing from this conversation. Carry the full intent, minimum context, owned files and scope, exact paths and artifacts, workspace choice, required checks, authorization bounds, and the origin thread ID and host.
Embed worker instructions: do the bounded task only and create no further tasks. On completion send ONE message to the origin with your thread ID and host, outcome, actual workspace and artifact paths, checks with results, and limitations; if unable to proceed, send a blocker instead. End your turn after that message. The callback is an internal handoff, not publication.
What ships with it
2 files 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.
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 · 46 lines · 58 tokens per session scan A 28626a7fa7da
codex-relay is a skill published in the GitHub repository DannyMac180/skills (628 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 759 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 2026-09-15.
Other skills, from other repositories
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…
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…
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.