agentmods.dev

OpenSDL: Skill for Claude Code

.agents/skills/start-here/SKILL.md

start-here is a skill for Claude Code, Codex from fl-sean03/OpenSDL. It costs 61 tokens per session (786 once invoked), scanned A, original, Apache-2.0.

A guided setup process for an OpenSDL laboratory, meaning a lab described and planned through files and workflows before or alongside real equipment. It can start a new lab or continue an existing one.

In plain words
What is it for?
Use it to set up or resume a lab, describe equipment, plan a new lab or cell, and create a simulator-first workflow plan.
Why use it?
It turns a broad laboratory idea into a clear first outcome and implementation plan, while recording equipment, data, constraints, hazards, and unknowns.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is fl-sean03/OpenSDL's own configuration. It tells Claude Code and Codex how to work on OpenSDL itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OpenSDL configures →

not rated 108repo +1 5d ago A scan SkillSpector: pass 61 tokens original Apache-2.0
View source ↗ fl-sean03/OpenSDL seanflorez.com
Reuse

Borrowing it

Nothing to install: this file belongs to fl-sean03/OpenSDL. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fl-sean03/OpenSDL/main/.agents/skills/start-here/SKILL.md
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 start-here

README.md
[![agentmods](https://agentmods.dev/badge/skills/fl-sean03/opensdl/start-here/github.svg)](https://agentmods.dev/skills/fl-sean03/opensdl/start-here)
Your own site
<a href="https://agentmods.dev/skills/fl-sean03/opensdl/start-here"><img src="https://agentmods.dev/badge/skills/fl-sean03/opensdl/start-here/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for start-here

Your own site · 80×15
<a href="https://agentmods.dev/skills/fl-sean03/opensdl/start-here"><img src="https://agentmods.dev/badge/skills/fl-sean03/opensdl/start-here.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 786 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00061 $0.00786
Opus 5.5 $0.00024 $0.00314
Sonnet 5.5 $0.00012 $0.00157
Haiku 4.5 $0.00006 $0.00079

Measured 2mo ago against content hash 74afb216c517, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

start-here 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 2mo 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.

.agents/skills/start-here/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start or resume a laboratory

Inputs

  • intended laboratory outcome or first useful workflow
  • existing, planned, or hybrid setup
  • repository or proposed destination
  • known equipment, compute, manual work, samples, data, and locations
  • relevant constraints, hazards, and available evidence

Begin with partial input. Ask for only the highest-value missing information.

Procedure

  1. Read the nearest AGENTS.md. Inspect the worktree, branch, recent commits, and current directory before changing files.
  2. Determine whether the user is in this framework repository, a generated laboratory repository, or an uninitialized destination.
  3. When a separate lab repository is needed, collect its name, owner, and destination. Use create-lab only after the destination is confirmed and safe.
  4. In a lab repository, read docs/lab/context.md, inventory.md, setup-plan.md, and decisions.md when present. Then read opensdl.yaml and only the workflows needed for the task.
  5. Classify the setup as existing, greenfield, or hybrid. Identify the first outcome before trying to inventory the entire laboratory.
  6. Update the shared lab files with confirmed facts, evidence, assumptions, unknowns, constraints, and decisions. Keep the product-wide work list in docs/development/backlog.md.
  7. Track inventory evidence, integration, and visual-twin state separately. An inventory entry is not authority to execute equipment.
  8. Map the first workflow to resources, typed capabilities, simulators, manual steps, data, tests, and gaps. Prefer one complete simulation path over a broad incomplete configuration.
  9. Update executable manifests or workflows only from confirmed information and supported contracts. Run opensdl validate for any executable file changed.
  10. Record any custom 3D request in the lab setup plan with its purpose, source evidence, dimensions, and target workflow. An agent can build the tailored Blender scene directly in the laboratory repository. OpenSDL currently has no dedicated digital-twin command and intentionally has no model catalog.
  11. Hand the next task to create-lab, orient-lab, design-lab, add-capability, add-adapter, develop-workflow, add-domain-pack, or debug-run as appropriate. Use design-lab when the open question is physical or interface design rather than OpenSDL configuration.

Read the full file on GitHub · 64 lines

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. 2mo ago First seen · 64 lines · 61 tokens per session scan A 74afb216c517

Subscribe to this mod's changes

start-here is a skill published in the GitHub repository fl-sean03/OpenSDL (108 stars, last pushed 5d ago), licensed Apache-2.0. It adds 61 tokens to every session and 786 once invoked, about $0.0002 per session on Opus 5.5. 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.

PlanningPythonScientificautonomous-laboratorylab-automationreproducibilityscientific-computingself-driving-labs
Related

start-here compared with skills from other repositories

start-here next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
start-herefl-sean03/OpenSDLSkill1085d agoApache-2.0A61Claude Code, Codex
scitexscitex-ai/scitex-pythonSkill86yesterdayAGPL-3.0A123Claude Code
stx.cliscitex-ai/scitex-pythonSkill86yesterdayAGPL-3.0A33Claude Code, Codex
xarray-netcdfxjtulyc/awesome-rosetta-skillsSkill356mo agononeA40Claude Code, Codex
jupyter-notebookNousResearch/hermes-agentSkill261kyesterdayMITA18Claude Code, Codex
pennylaneK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA74Claude Code
cuequivariance-jaxNVIDIA/skillsSkill3.9kyesterdayApache-2.0A38Claude Code, Codex