optimize-workload

A guide for improving an AI prompt or model route using measured evaluation results, without retraining the model. It evolves prompts while keeping a reserved test set separate from the data used for improvement.

In plain words
What is it for?
Improving response quality, reducing model cost while protecting quality, and testing prompt changes against recorded evaluation data.
Why use it?
It prevents changes from being judged on the same examples used to create them, and refuses to proceed when required evaluation evidence is missing or outdated.

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

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,183 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 $0.00079 $0.03183
Opus 5 $0.00039 $0.01591
Sonnet 5 $0.00016 $0.00637
Haiku 4.5 $0.00008 $0.00318

Measured 2d ago against content hash 1678f8d62cf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimize-workload 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/optimize-workload/SKILL.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimize Workload

Use this worker only after the workload has fresh local artifacts from capture-evidence. Validation and optimization must be evidence-led and split-safe.

Safety Gates

Default to the intervention with the highest expected progress toward the objective under hard constraints, not the cheapest rung. State the expected quality gain, time, spend envelope, and evidence before execution; follow ../understudy/reference.md → Outcome-first spend posture. A developer action that launches a named bounded optimization plan authorizes its declared model calls, uploads, hosted work, evaluation, receipts, and cleanup. Do not pause for phase-by-phase confirmation. Ask again only if the plan expands its displayed data, destination, spend, retention, download, or production-impact envelope. Follow the repo public boundary in ../../docs/privacy-and-data-boundaries.md for prompts, completions, traces, labels, datasets, repo paths, secrets, and private notes.

Refusal Gate

Refuse to optimize unless all required artifacts are present and fresh:

.understudy/capture-evidence/harness.json
.understudy/capture-evidence/metric.json
.understudy/capture-evidence/splits.json
.understudy/capture-evidence/baseline.json

Fresh means generated for the same workload, metric, split contract, and incumbent baseline in the current task context. Freshness is hash-bound: baseline.json must include harness_sha256, metric_sha256, and splits_sha256, and those values must match the current harness.json, metric.json, and splits.json. If freshness is ambiguous or hashes do not match, route back to ../capture-evidence/SKILL.md instead of optimizing.

Split Rules

  • GEPA is train/dev-only.
  • Prompt, route, parser, renderer, and candidate selection changes may use train and dev only.
  • Never mutate holdout rows, labels, validators, thresholds, or sampling after optimization begins.
  • Holdout is only for final validation after the candidate is frozen.
  • If holdout is touched accidentally, mark the result contaminated and create a new split contract before claiming progress.

Read the full file on GitHub · 261 lines

Files

What ships with it

7 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 · 261 lines · 79 tokens per session scan A 1678f8d62cf6

Subscribe to this mod's changes

optimize-workload is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 3,183 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 2026-08-30.

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