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 yipp2025-codex/local-codex-bridge --skill stateful-relay-orchestratorgit clone --depth 1 https://github.com/yipp2025-codex/local-codex-bridgeWrote 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/yipp2025-codex/local-codex-bridge/stateful-relay-orchestrator)<a href="https://agentmods.dev/skills/yipp2025-codex/local-codex-bridge/stateful-relay-orchestrator"><img src="https://agentmods.dev/badge/skills/yipp2025-codex/local-codex-bridge/stateful-relay-orchestrator/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/yipp2025-codex/local-codex-bridge/stateful-relay-orchestrator"><img src="https://agentmods.dev/badge/skills/yipp2025-codex/local-codex-bridge/stateful-relay-orchestrator.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 | $0.00040 | $0.00595 |
| Opus 5 | $0.00020 | $0.00298 |
| Sonnet 5 | $0.00008 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
stateful-relay-orchestrator 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 10d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stateful Relay Orchestrator
Use this skill only with the existing Stateful Relay and Operator contract.
Authority
- GPT is the planning and review authority. GPT decides what should happen, dispatches through the fixed Relay surface, and independently reviews returned evidence. ACK is delivery acknowledgement, not review.
- Relay is the durable state and notification authority. Relay owns task lineage, claim and result transitions, correlation, and delivery state.
- Native Codex is the execution authority. A normal Native Codex session claims bounded work and reports execution and evidence through Relay.
- Operator is a facade only. Operator has no execution authority.
GPT-side workflow
dispatchsends the existing fixed read-only classroom task.dispatch_bounded_writemay be used only after a separate explicit authorization and only for the fixedinstall_stateful_relay_orchestrator_skill_v1operation. The caller supplies no path, target root, leaf, cwd, shell, process, command, environment, credential, or arbitrary prompt.resultsreads the durable Codex result body and evidence from Relay. Do not treat a notification acknowledgement as a review.statusreads bounded Relay state without executing, acknowledging, reclaiming, or reviewing work.resumereads recoverable Relay inbox state and does not silently retry or create a second task.
For every result, verify task identity, project identity, client request identity, request/body hashes, revision, operation, target scope, correlation, and the reported authority attribution. For bounded writes, also verify the exact payload manifest, changed paths, collision status, before/after manifests, and independent readback before review.
Native Codex-side workflow
inboxclaims only the task selected by the authenticated Native Codex mailbox.reportsubmits the result and evidence for the current claim through Relay.
Native Codex must revalidate the fixed operation, deployment-owned target mapping, canonical physical scope, frozen payload manifest, collision state, and correlation before any authorized mutation. Any mismatch is a failed, fail-closed result. Do not use a fallback shell, subprocess, arbitrary filesystem path, or a second mutation to repair a failed result.
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.
- 10d ago First seen · 44 lines · 40 tokens per session scan A f4dd8ed7d534
stateful-relay-orchestrator is a skill published in the GitHub repository yipp2025-codex/local-codex-bridge (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 595 once invoked, about $0.0002 per session on Opus 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…