reference-images

reference-images is a skill for Claude Code, Codex from ukanwat/aaabench. It costs 49 tokens per session (1,095 once invoked), scanned A, original, MIT.

A workflow for finding, downloading, and looking at real photographs as visual references. It is useful when creating believable places, materials, vehicles, skies, or lighting.

In plain words
What is it for?
Use it to search for reference photos, save them locally, inspect them, and compare details such as building surfaces, roads, wear, shadows, and color.
Why use it?
Text search results do not let you inspect the actual image, so important details can be missed. Comparing real photos with your own work helps reveal specific differences to correct.

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/ukanwat/aaabench/reference-images
Any agent
npx skills add ukanwat/aaabench --skill reference-images
Clone the repo
git clone --depth 1 https://github.com/ukanwat/aaabench

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 reference-images

README.md
[![agentmods](https://agentmods.dev/badge/skills/ukanwat/aaabench/reference-images.svg)](https://agentmods.dev/skills/ukanwat/aaabench/reference-images)
Your own site
<a href="https://agentmods.dev/skills/ukanwat/aaabench/reference-images"><img src="https://agentmods.dev/badge/skills/ukanwat/aaabench/reference-images.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,095 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.01095
Opus 5 $0.00024 $0.00548
Sonnet 5 $0.00010 $0.00219
Haiku 4.5 $0.00005 $0.00110

Measured 4d ago against content hash a1e0648e0ad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reference-images scanned grade A with 1 finding 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.

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.

Makes network callslowCapability

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

curl -s -A "agent/1.0" \
.claude/skills/reference-images/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Looking at real photographs

WebSearch returns text and WebFetch returns markdown — neither gives you an image. To see a photo you must download it and Read the file:

mkdir -p ref/strand
# 1. SEARCH — Openverse: CC-licensed, no API key. KEEP QUERIES TO 2–3 WORDS.
#    Every term is ANDed, so "miami south beach art deco dusk" returns ZERO results.
curl -s -A "agent/1.0" \
  "https://api.openverse.org/v1/images/?q=art+deco+hotel&page_size=8" \
  | python3 -c "import json,sys; [print(r['url']) for r in json.load(sys.stdin)['results']]"

# 2. DOWNLOAD
curl -sL -A "agent/1.0" -o ref/strand/deco1.jpg "<url from above>"

# 3. LOOK at it — Read the local file; images render for you.

Then read your own screenshot of the same subject and name the gap out loud: "real facades have setbacks, AC units and stained concrete; mine are flat", "the real kerb has a ramp, a drain and a meter every third car; mine is a clean extrusion", "real asphalt is bluer, patched, and the lane paint is worn through in the wheel tracks", "the real light is warmer and lower and the shadows are longer". A named gap is a work item; "make it better" is not.

Sources that need no key (all verified working)

  • Openverse — keyword photo search, direct image URLs. The everyday default. https://api.openverse.org/v1/images/?q=<2-3+words>&page_size=10 Trap: multi-word queries are ANDed. Two or three words, or you get nothing.
  • Wikimedia Commons search — landmarks, aerials, named buildings. https://commons.wikimedia.org/w/api.php?action=query&generator=search&gsrsearch=<query>&gsrnamespace=6&gsrlimit=5&prop=imageinfo&iiprop=url&iiurlwidth=1600&format=json Send a User-Agent. gsrnamespace=6 is required. Do NOT add filetype:bitmap — it breaks the query and no query key comes back. Read imageinfo[0].thumburl.
  • Wikimedia geosearch — every photo taken near a real coordinate. This is how you study a real place rather than a word. https://commons.wikimedia.org/w/api.php?action=query&generator=geosearch&ggscoord=<lat>%7C<lon>&ggsradius=1000&ggslimit=10&ggsnamespace=6&prop=imageinfo&iiprop=url&iiurlwidth=1600&format=json
  • KartaView — street-level photography from a car windscreen, at any coordinate. https://api.openstreetcam.org/2.0/photo/?lat=<lat>&lng=<lng>&radius=400 Read result.data[].fileurlProc. The most valuable source you have: it is your exact game camera — driver eye height, kerb to kerb, real parked-car spacing, real pole and cable spans, real sky. One of these tells you more about how a street reads than an hour of guessing.
  • Aerial/satellite imagery of a real city: see the map-data source doc.

Read the full file on GitHub · 71 lines

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 · 71 lines · 49 tokens per session scan A a1e0648e0ad0

Subscribe to this mod's changes

reference-images is a skill published in the GitHub repository ukanwat/aaabench (378 stars, last pushed 20d ago), licensed MIT. It adds 49 tokens to every session and 1,095 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (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

benchjack

Audit an AI agent benchmark for hackability. Detects evaluation vulnerabilities like missing isolation, leaked answers, eval() on untrusted input, prompt injection in LLM judges, weak scoring, logic gaps, and trust of untrusted output. Use when analyzing whether a benchmark can be gamed or exploited.

benchjack/benchjack · 63 tokens

unreal-pie

Domain skill - Unreal Engine Play-In-Editor (PIE) closed-loop verification. Provides PIE lifecycle control (enter/pause/resume/exit), controlled input injection (no OS dependency), viewport screenshot capture, output log snapshot, performance sampling, and Automation Test execution with async job polling. Use for…

dcc-mcp/dcc-mcp-unreal · 74 tokens

unreal-playtest-agent

Domain skill - run screenshot-light PIE playtest episodes with structured entity observations, bounded semantic actions, transition polling, and in-memory traces for QA and external policy or RL runners.

dcc-mcp/dcc-mcp-unreal · 41 tokens

unreal-actors

Domain skill - Unreal Engine actor management: list, spawn, transform, and delete level actors. Use when inspecting or editing actors in the current Unreal Editor level. Not for Content Browser asset import/export - use unreal-assets for that.

dcc-mcp/dcc-mcp-unreal · 51 tokens

unreal-cinematics

Domain skill — Sequencer shot and keyframe orchestration, camera cut tracks, and Movie Render Queue job setup. Use when creating or editing Level Sequences, authoring camera animation, or preparing an MRQ job in Unreal Engine 5. Not for Blueprint scripting (unreal-blueprints) or runtime playback (unreal-runtime).

dcc-mcp/dcc-mcp-unreal · 72 tokens

unreal-fab-assets

Acquire free Fab marketplace content through Unreal Engine's official Fab integration, then verify the imported Content Browser assets. Use when the user asks to find, download, add, or import Fab or Unreal Marketplace assets. Not for arbitrary file imports - use unreal-assets instead.

dcc-mcp/dcc-mcp-unreal · 58 tokens