What is local-vision-router?

Instructions for inspecting local image files through a configured vision service and returning a text description or reading of what they contain.

Use it to describe images, transcribe visible text, review interface layout, check visual states, and identify clipping, contrast, or alignment issues.

They let a text-only coding agent review screenshots and other images without guessing about visual details.

local-vision-router — Skill for Codex by krunkosaurus

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 krunkosaurus/codex-local-vision-router --skill local-vision-router

Clone the repo

git clone --depth 1 https://github.com/krunkosaurus/codex-local-vision-router

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/krunkosaurus/codex-local-vision-router/local-vision-router/github.svg)](https://agentmods.dev/skills/krunkosaurus/codex-local-vision-router/local-vision-router)

Your own site

<a href="https://agentmods.dev/skills/krunkosaurus/codex-local-vision-router/local-vision-router"><img src="https://agentmods.dev/badge/skills/krunkosaurus/codex-local-vision-router/local-vision-router/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/krunkosaurus/codex-local-vision-router/local-vision-router"><img src="https://agentmods.dev/badge/skills/krunkosaurus/codex-local-vision-router/local-vision-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 377 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	$0.00071	$0.00377
Opus 5	$0.00036	$0.00188
Sonnet 5	$0.00014	$0.00075
Haiku 4.5	$0.00007	$0.00038

Measured 9d ago against content hash 1a8e8a981f02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

local-vision-router 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 9d 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/local-vision-router/SKILL.md · 39 lines

What it actually says

Local Vision Router

Use local_vision.describe_image as the only pixel-reading tool in a text-only primary-model session. The tool sends the local image to the configured vision endpoint and returns a bounded plain-text observation.

Workflow

Resolve the requested image to an absolute local path.
Call local_vision.describe_image with image_path and a focused prompt.
Use the returned text as visual evidence in the answer.
State uncertainty when the vision response is ambiguous.

For a general inspection, request the main subject, composition, visible text, and uncertainty. For OCR, request exact transcription and preserve line breaks. For UI review, request layout, states, errors, clipping, contrast, and alignment.

Text-only boundary

Do not call Codex's built-in view_image tool in a text-only session.
Do not attach or embed image data in the primary model request.
If no absolute path is available, ask the user to save the image locally and provide its path.
Never infer details absent from the tool response.

Failures

If the endpoint is unavailable, tell the user to start its local server and load the configured vision model.
If the tool reports a relative path, retry only after resolving an absolute path.
If the primary session already contains an incompatible image block, start a new session rather than resuming the poisoned history.

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 422 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.

9d ago First seen · 39 lines · 71 tokens per session scan A 1a8e8a981f02

Subscribe to this mod's changes

local-vision-router is a skill published in the GitHub repository krunkosaurus/codex-local-vision-router (0 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 377 once invoked, about $0.0004 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.

Design and UX

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

local-vision-router