test-codex-locally

test-codex-locally is a skill for Claude Code, Codex from workweave/router. It costs 98 tokens per session (4,960 once invoked), scanned D, original, no licence file.

A local end-to-end test procedure for running the Weave Router in Docker Compose and driving it with codex exec. It checks routing, translation, and marker behavior for Codex's Responses API path.

In plain words
What is it for?
Use it to test router changes, investigate production Codex routing problems, and check force-model or routing-marker behavior.
Why use it?
It helps reproduce Codex routing bugs locally and verify that a router fix works through the full request path.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/workweave/router/test-codex-locally
Any agent
npx skills add workweave/router --skill test-codex-locally
Clone the repo
git clone --depth 1 https://github.com/workweave/router

Made for: Claude Code, 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.

agentmods badge for test-codex-locally

README.md
[![agentmods](https://agentmods.dev/badge/skills/workweave/router/test-codex-locally.svg)](https://agentmods.dev/skills/workweave/router/test-codex-locally)
Your own site
<a href="https://agentmods.dev/skills/workweave/router/test-codex-locally"><img src="https://agentmods.dev/badge/skills/workweave/router/test-codex-locally.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,960 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. Scan, not verified.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5 $0.00098 $0.04960
Opus 5 $0.00049 $0.02480
Sonnet 5 $0.00020 $0.00992
Haiku 4.5 $0.00010 $0.00496

Measured 4d ago against content hash 9e000b27a742, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

test-codex-locally scanned grade D with 3 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/mock_codex_upstream.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

> For an **automated** pre-merge regression net (fixture-driven, asserts caching/streaming/decision-headers against real Anthropic), run `make smoke` — see [docs/SMOKE.md](../../../docs/SMOKE.md). This skill is the inter

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$CODEX_HOME"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Session key is `apiKeyID` + first user message.** Reusing the same curl/prompt body on the same key reuses the pin slot. `routingMarkerFor` then returns empty when `PriorServedModel == ServedIdentity()` (sticky same-
.claude/skills/test-codex-locally/SKILL.md · 255 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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.

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.

  1. 4d ago First seen · 255 lines · 98 tokens per session scan D 9e000b27a742

Subscribe to this mod's changes

test-codex-locally is a skill published in the GitHub repository workweave/router (3,743 stars, last pushed today), with no licence file. It adds 98 tokens to every session and 4,960 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 3 findings (reads agent configuration directories, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

config-platform-change

Synchronizes config representations across router config, Python CLI schema, and dashboard config UI. Use when adding or changing a config concept that spans those surfaces or addressing config representation debt before Kubernetes-facing translation.

vllm-project/semantic-router · 43 tokens

oma-translation

Context-aware translation that preserves tone, style, and natural word order. Use when translating UI strings, documentation, marketing copy, or any multilingual content. Infers register, domain, and style from the source text and surrounding codebase context.

first-fluke/oh-my-agent · 52 tokens

nw-bdd-requirements

BDD requirements discovery methodology - Example Mapping, Three Amigos, conversational patterns, Given-When-Then translation, and collaborative specification.

nWave-ai/nWave · 31 tokens

hns-oss-docs-i18n-rules

HARD i18n rules digest for the oss-docs harness specialists working on moai-adk-go README 4-locale set and the docs-site (adk.mo.ai.kr). Covers the canonical-locale chains, the 4-locale same-PR obligation, Mermaid TD-only, the no-emoji + icon-shortcode rule, emphasis-marker spacing, the URL blacklist, version SSOT…

modu-ai/moai-adk · 119 tokens

qa-evaluation

Evidence-driven QA evaluation for 1flowbase dev acceptance, PR merge gates, project health gates, regression, stale or incompatible test expectation triage, delivery, full-project and AI code audits, quality gate routing, i18n/multilingual key-value hygiene, frontend/backend contracts, console settings registry and…

taichuy/1flowbase · 146 tokens

frontend-development

Use for 1flowbase frontend implementation in web/: building, fixing, refactoring, or code-reviewing UI pages, app shell, routes, workspace flows, node UI, schema UI, i18n resources, responsive layout, visual structure, ECharts/reporting UI, low-code JS Block chart primitives, or frontend state boundaries. Use after…

taichuy/1flowbase · 106 tokens