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/use-understudy-gatewaynpx skills add understudylabs/understudy-agent-tools --skill use-understudy-gatewaygit clone --depth 1 https://github.com/understudylabs/understudy-agent-toolsWrote 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.
[](https://agentmods.dev/skills/understudylabs/understudy-agent-tools/use-understudy-gateway)<a href="https://agentmods.dev/skills/understudylabs/understudy-agent-tools/use-understudy-gateway"><img src="https://agentmods.dev/badge/skills/understudylabs/understudy-agent-tools/use-understudy-gateway.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00087 | $0.03566 |
| Opus 5 | $0.00044 | $0.01783 |
| Sonnet 5 | $0.00017 | $0.00713 |
| Haiku 4.5 | $0.00009 | $0.00357 |
Grade A, and why
use-understudy-gateway 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 3d 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Understudy Gateway
Use this worker when the developer wants to run an application workload through Understudy-managed inference or needs the CLI to execute a durable command while the agent monitors status and artifacts.
The local evidence loop does not require auth. Route here only when the developer explicitly asks for Understudy inference, gateway routing, project/key management, workload route configuration, hosted execution, or authenticated gateway routing.
Choosing frontier access? When an onboarding step, installer, or
local-vs-frontier comparison needs a remote frontier model, run the decision in
references/frontier-keys.md first. Default to
the Understudy managed catalog when the requested model is available there; use
BYO shell/.env keys only for unsupported models, provider-specific account
needs, or an explicit developer preference. It keeps secrets local, asks before
reading .env values, and records the choice without printing keys.
Safety Gates
Do not ask the developer to paste an API key. Use the CLI registration flow and let the CLI store credentials outside the repo.
Do not print, commit, or write sk_* values into artifacts. understudy run
injects UNDERSTUDY_API_KEY, UNDERSTUDY_GATEWAY_URL, and the non-secret
UNDERSTUDY_ORG_ID when known only into the child process environment.
The developer's action that launches a named bounded workflow authorizes its declared provider calls, uploads, hosted jobs, evaluation, receipts, and cleanup. Do not pause for another confirmation between those phases. Ask again only before expanding the displayed data, destination, spend, retention, download, credential, or production-impact envelope.
Always stream gateway inference
Every inference request sent to the Understudy gateway (/v1/messages or
/v1/chat/completions) must set stream: true. This is not a style
preference: the gateway sits behind an edge that cuts any origin response
producing no first byte within ~125 seconds and returns a 524 to the client.
A non-streaming request holds the response open for the model's full
generation time, so a slow generation can cross that limit and fail — and a
524 carries no usage block, so the request's tokens cannot be metered. With
stream: true the upstream returns headers and SSE framing within seconds,
so the first-byte timeout can never fire regardless of generation length.
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.
- 3d ago First seen · 323 lines · 87 tokens per session scan A cd9aa796ff02
use-understudy-gateway is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 3,566 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…