orient-lab

orient-lab is a skill for Claude Code, Codex from fl-sean03/OpenSDL. It costs 49 tokens per session (448 once invoked), scanned A, original, Apache-2.0.

A read-only inspection procedure for understanding the current state of an OpenSDL laboratory repository. It checks the repository instructions, declared lab configuration, equipment connections, capabilities, storage, and policies.

In plain words
What is it for?
Use it to inspect the current branch and changes, validate a lab manifest, review shared lab context, and understand the environment, adapters, workflows, and policies in use.
Why use it?
It gives developers a reliable starting picture before they change a lab or investigate a task. It helps distinguish declared plans and inventory from evidence recorded by the running system.

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/orient-lab
Any agent
npx skills add fl-sean03/OpenSDL --skill orient-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 orient-lab

README.md
[![agentmods](https://agentmods.dev/badge/skills/fl-sean03/opensdl/orient-lab.svg)](https://agentmods.dev/skills/fl-sean03/opensdl/orient-lab)
Your own site
<a href="https://agentmods.dev/skills/fl-sean03/opensdl/orient-lab"><img src="https://agentmods.dev/badge/skills/fl-sean03/opensdl/orient-lab.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 448 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 $0.00049 $0.00448
Opus 5 $0.00024 $0.00224
Sonnet 5 $0.00010 $0.00090
Haiku 4.5 $0.00005 $0.00045

Measured 5d ago against content hash 32e1c6cdf964, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orient-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 5d 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/orient-lab/SKILL.md · 45 lines

What it actually says

Orient to a laboratory

Inputs

  • manifest path
  • optional run identifier or workflow path that defines the current task

Use start-here instead when the user is establishing the lab, changing its setup plan, or adding newly reported equipment.

Procedure

  1. Read the nearest AGENTS.md and inspect git status --short, the branch, and recent commits.
  2. Read the shared laboratory context under docs/lab/ when present. Treat facts, assumptions, decisions, inventory evidence, and lab-specific work as planning context rather than runtime evidence.
  3. Read the selected manifest and identify its environment, storage, adapters, capabilities, resources, and policy version.
  4. Run .agents/skills/orient-lab/run.sh MANIFEST to validate files without opening the runtime store.
  5. Read only the architecture and workflow files needed for the user's task.
  6. doctor, capability listing, run inspection, and event queries read without writing: they compose the laboratory read-only and refuse to create a store that is not there. doctor reconciles incomplete runs only when asked with --reconcile, and reports what it moved.
  7. Never pass --reconcile while work may be in flight: it moves every running run to intervention_required and releases its leases, which is recovery after a controller stopped, not a health check.
  8. Report current evidence, mismatches, active assumptions, and commands that are unavailable.

Completion

The user receives an on-demand summary tied to the current Git revision, validated manifest, declared environment, adapters, capabilities, resources, and policy. Any runtime evidence is marked as a state-touching query.

Stop conditions

Stop if the manifest is missing or validation fails. Do not infer health, active runs, or physical state from declared configuration.

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. 5d ago First seen · 45 lines · 49 tokens per session scan A 32e1c6cdf964

Subscribe to this mod's changes

orient-lab is a skill published in the GitHub repository fl-sean03/OpenSDL (102 stars, last pushed 5d ago), licensed Apache-2.0. It adds 49 tokens to every session and 448 once invoked, about $0.0002 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