ladder

A small local web page that lets you watch a local language model and a frontier model try the same task side by side. A local model runs on your own computer; a frontier model is a larger, remotely hosted model.

In plain words
What is it for?
Use it to explore whether a local model is suitable, compare local and frontier models, and see tool use and scoring on a shared task.
Why use it?
It gives you a concrete comparison before you have collected examples from your own work. You can see where the smaller model keeps up and where the larger one does better.

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/understudylabs/understudy-agent-tools/ladder
Any agent
npx skills add understudylabs/understudy-agent-tools --skill ladder
Clone the repo
git clone --depth 1 https://github.com/understudylabs/understudy-agent-tools

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,588 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 $0.00084 $0.01588
Opus 5 $0.00042 $0.00794
Sonnet 5 $0.00017 $0.00318
Haiku 4.5 $0.00008 $0.00159

Measured 2d ago against content hash 3585a2a1220b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ladder 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (env/world.py, serve.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.

Makes network callslowCapability

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

curl -N 'http://localhost:8011/run?task=sort-email&model=gemma-4-e2b'
skills/ladder/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ladder — the onboarding "climb"

A small, self-contained local web UI for watching and comparing LLMs on the same task. It is the no-data front door: a developer launches it and watches a small local model and a frontier model attempt the same task side by side — live reasoning, real tool calls, strict scoring — without needing any of their own traces first. As the task gets harder, the small local model keeps pace and then drops off where the frontier model carries on. That contrast is the hook into the rest of the improvement loop.

When to use

  • A new user asks "what can a local model actually do?" / "is a small model good enough?" / "show me local vs frontier."
  • During or right after onboard, to make the local-vs-frontier difference concrete before steering them toward their own workload.
  • Any time a visceral, zero-setup-data demo of agentic behavior + scoring helps.

For the user's own eval across many candidate models, hand off to compare-model-sweep. To serve a local model against the user's real workload, hand off to run-local-model-lab.

Run it

Prerequisites (otherwise-silent assumptions):

  • Apple Silicon (arm64) Mac with uv on PATH — the local lane needs a current mlx stack (system mlx_lm is often too old to load the model).
  • The local model cached at ~/.understudy/models/gemma-4-e2b-it-qat-mlx-vlm-understudy — the gemma-4-e2b id resolves to that directory, not a dir literally named gemma-4-e2b. If it's missing, pull it with the manage-local-models skill (understudy models pull gemma-4-e2b-it-qat-mlx-vlm-understudy); the server prints an actionable error if it's absent.
  • Remote lanes only: run understudy login once so understudy run can inject the gateway key and org id. Without it a remote lane returns the literal notice [gateway not configured …] rather than erroring — don't mistake that for a real run.

Run from the repo root (the path below is relative):

understudy run -- uv run --with mlx-vlm --with mlx-lm python skills/ladder/serve.py

Read the full file on GitHub · 126 lines

Files

What ships with it

8 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.

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. 2d ago First seen · 126 lines · 84 tokens per session scan A 3585a2a1220b

Subscribe to this mod's changes

ladder is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 1,588 once invoked, about $0.0004 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.