understudy

A workflow for improving applications that use large language models, the systems behind tools such as chatbots and coding agents. It guides the agent through examining real usage, testing results, improving prompts or model choices, and preparing changes for use.

In plain words
What is it for?
Use it to trace LLM calls, inspect prompts and datasets, evaluate outputs, compare models or settings, and plan an improvement workflow.
Why use it?
It provides a structured way to investigate whether an LLM system needs better quality, lower cost, faster responses, or greater reliability.

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

Made for: Claude Code, Codex.

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,154 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00092 $0.06154
Opus 5 $0.00046 $0.03077
Sonnet 5 $0.00018 $0.01231
Haiku 4.5 $0.00009 $0.00615

Measured 2d ago against content hash 229967b2e809, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

understudy 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 2d 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/understudy/SKILL.md · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Understudy

Understudy is agent improvement infrastructure: it helps a coding agent improve its developer's LLM system from real traces. This skill is the orchestrator — it gives your agent the loop and routes each stage to exactly one worker skill. It does not do the work inline.

The loop is backend-agnostic: it can begin locally without registration, but the default route is the strongest active model and managed cloud execution when the developer has not selected Local. A dropped dataset authorizes analysis through the active model. Activating a named, bounded cloud workflow authorizes its normal uploads, provider calls, temporary resources, evaluation, receipts, and cleanup.

The improvement loop

  1. Understand the codebase — find where LLM calls happen and the current model / provider / harness / routing / eval setup.
  2. Understand the objective (cost, speed, quality, reliability, compliance, or a weighted mix).
  3. Understand the constraints (what must not be violated).
  4. Understand the workload — inspect prompts in situ, trace the request/response code path, profile the dataset/traces, and confirm the task meaning with the user.
  5. Capture or locate real traces.
  6. Build or improve a decision-sized, representative eval harness; rerun the incumbent baseline.
  7. Run local optimization against eval failures.
  8. Compare candidate vs baseline on the objective.
  9. Recommend the best route for the stated objective — harness, model, supplier, gateway/inference-layer route, deployment approach — with cost and time transparent.
  10. Implement the selected route safely with the smallest coherent change that fully addresses the measured cause.
  11. Produce an Understudy Agent Improvement Report the developer can review.

Frame every job

Keep these six separate and explicit — say them back before acting:

  • Objective — what are we optimizing for?
  • Constraints — what are we not allowed to violate?
  • Evidence — what traces / evals / prices / measurements do we have?
  • Workload — what task does the prompt/data/code path actually represent?
  • Route — what harness / model / supplier / deployment path?
  • Action — what does the agent actually change?
  • Verification — how do we prove the change helped?

Read the full file on GitHub · 449 lines

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. 2d ago First seen · 449 lines · 92 tokens per session scan A 229967b2e809

Subscribe to this mod's changes

understudy is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session and 6,154 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens