create-lab

create-lab is a skill for Claude Code, Codex from fl-sean03/OpenSDL. It costs 29 tokens per session (360 once invoked), scanned A, original, Apache-2.0.

A starter structure for an organization’s OpenSDL laboratory repository, including its policies, checks, workflows, and local agent instructions. OpenSDL is a framework for computational and autonomous laboratories.

In plain words
What is it for?
Use it to bootstrap a lab from an empty folder, configure its OpenSDL package source, run its checks and first simulated workflow, and gradually replace simulated capabilities.
Why use it?
It gives a new lab a tested baseline and makes clear which capabilities are simulated until real ones are added. This helps separate local setup work from the framework itself.

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/fl-sean03/opensdl/create-lab
Any agent
npx skills add fl-sean03/OpenSDL --skill create-lab
Clone the repo
git clone --depth 1 https://github.com/fl-sean03/OpenSDL

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for create-lab

README.md
[![agentmods](https://agentmods.dev/badge/skills/fl-sean03/opensdl/create-lab.svg)](https://agentmods.dev/skills/fl-sean03/opensdl/create-lab)
Your own site
<a href="https://agentmods.dev/skills/fl-sean03/opensdl/create-lab"><img src="https://agentmods.dev/badge/skills/fl-sean03/opensdl/create-lab.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 360 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 $0.00029 $0.00360
Opus 5 $0.00015 $0.00180
Sonnet 5 $0.00006 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured 3d ago against content hash 4255cea905a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-lab 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.

The scan reads SKILL.md. This mod also ships 1 executable file (run.sh), 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.

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.

.agents/skills/create-lab/SKILL.md · 40 lines

What it actually says

Create an organization laboratory

Inputs

  • empty destination path
  • laboratory name
  • owner identifier

Procedure

  1. Run .agents/skills/create-lab/run.sh PATH [NAME] [OWNER].
  2. Inspect the generated manifest, workflows, policy, tests, and local skills.
  3. Configure a package source for the OpenSDL alpha distributions.
  4. For a local smoke test before registry publication, run uv build --all-packages --wheel --out-dir dist in the framework checkout. Then run uv sync --find-links /path/to/OpenSDL/dist in the lab.
  5. Run ./scripts/check.sh and the first simulator workflow.
  6. Prepare an organization-owned baseline. Commit it when requested and only treat uv.lock as portable when it resolves from a stable registry or committed artifact source. A local wheelhouse path can be recorded in the lock and is local bootstrap state.
  7. Set the CI repository variable OPENSDL_PACKAGES_AVAILABLE=true only after that stable source is available. Until then, CI validates agent files and visibly skips the full dependency-backed job.
  8. Replace simulated capabilities incrementally and retain their conformance fixtures.

Completion

With an OpenSDL package source configured, the separate repository resolves its dependencies and passes its generated simulator checks. A stable package source is required before claiming that the lockfile and generated CI are portable across clones.

Stop conditions

Stop if the destination contains files or package resolution is unavailable. Report the exact state and preserve the destination.

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. 3d ago First seen · 40 lines · 29 tokens per session scan A 4255cea905a5

Subscribe to this mod's changes

create-lab is a skill published in the GitHub repository fl-sean03/OpenSDL (102 stars, last pushed 3d ago), licensed Apache-2.0. It adds 29 tokens to every session and 360 once invoked, about $0.0001 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.