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.
npx agentmods add skills/understudylabs/understudy-agent-tools/optimize-agentic-workloadnpx skills add understudylabs/understudy-agent-tools --skill optimize-agentic-workloadgit clone --depth 1 https://github.com/understudylabs/understudy-agent-toolsWhat 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 | $0.00077 | $0.03942 |
| Opus 5 | $0.00039 | $0.01971 |
| Sonnet 5 | $0.00015 | $0.00788 |
| Haiku 4.5 | $0.00008 | $0.00394 |
Grade A, and why
optimize-agentic-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.
How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize Agentic Workload
Use this worker when the workload is an agentic loop: an LLM that plans over multiple turns and calls tools (web search, retrieval, REST/SDK calls, code execution) before finishing. Freeze every non-target variable within each experiment; model/route comparisons hold the tools fixed, while a named implementation arm may isolate one deployable tool, app, or harness change. The goal is to pick the route and implementation you would ship on a multi-objective basis — quality and latency and cost (and, for workflows that write, side-effect safety). The route is backend-agnostic: use the existing harness, provider-native evaluation or training, the public CLI, or a small versioned app/harness change when the measured failure calls for it.
The one discriminator that changes the playbook is whether the loop mutates state:
- Read-only search loops — web/agentic search, retrieval, lookup tools.
Success depends on how the agent searches and the final answer; determinism
comes from snapshotting live tool outputs. Harness specifics:
references/read-only-search.md. - State-mutating API workflows — the agent discovers or selects endpoints,
follows policy docs, performs writes across business systems, and is judged
by final state plus policy compliance. Determinism comes from seeded,
resettable state; safety (no forbidden writes) is a first-class objective.
Harness specifics:
references/state-mutating-workflows.md.
Everything else — the artifact contract, measured baseline, workload-specific decision contract, evidence-driven intervention choice, and stronger RL gates — is shared.
This is not the RL handoff skill. Reach for
../prepare-verifier-handoff/SKILL.md
only when the evidence shows the residual requires reinforcement learning of
stateful behavior and its reward and renderer gates pass. Supervised
fine-tuning or distillation is a separate intervention and can be selected
earlier when correction labels or deterministic verifier targets support it.
What ships with it
2 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.
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.
- 2d ago First seen · 311 lines · 77 tokens per session scan A 1bd9548893d7
optimize-agentic-workload is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 3d ago), licensed MIT. It adds 77 tokens to every session and 3,942 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…