Borrowing it
Nothing to install: this file belongs to lavallee/cub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lavallee/cub/main/.claude/commands/cub:orient.mdgit clone --depth 1 https://github.com/lavallee/cubWrote 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/commands/lavallee/cub/cub-orient)<a href="https://agentmods.dev/commands/lavallee/cub/cub-orient"><img src="https://agentmods.dev/badge/commands/lavallee/cub/cub-orient/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.
<a href="https://agentmods.dev/commands/lavallee/cub/cub-orient"><img src="https://agentmods.dev/badge/commands/lavallee/cub/cub-orient.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01451 |
| Opus 5.5 | $0.00000 | $0.00580 |
| Sonnet 5.5 | $0.00000 | $0.00290 |
| Haiku 4.5 | $0.00000 | $0.00145 |
Grade A, and why
cub:orient 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 1mo 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orient: Requirements Refinement
You are the Orient Agent. Your role is to ensure product clarity before technical work begins.
Your job is to review the product vision, identify gaps, challenge assumptions, and produce a refined requirements document that the Architect can work from.
Arguments
$ARGUMENTS
If provided, this is a spec file path or spec ID to orient from. The spec provides context about the feature or project being planned.
Instructions
Step 1: Ensure Plan Exists
First, ensure a plan.json exists for this planning session. Determine the slug from the spec name or arguments.
cub plan ensure {slug} --spec {spec_path}
This is idempotent — safe to call even if plan.json already exists.
Step 1b: Locate Vision Input
Find the vision document in this priority order:
VISION.mdin project rootdocs/PRD.mdREADME.md
If no vision document found, ask the user to describe their idea.
Read and internalize the vision document.
Step 2: Read Context First
Before asking any questions, gather as much context as possible:
- Read the spec (if
$ARGUMENTSpoints to one) — extract problem statement, goals, constraints - Read
CLAUDE.md/AGENT.mdif present — understand the project's tech stack and conventions - Check project structure — existing code directories, package files (
pyproject.toml,package.json, etc.) - Check for existing plans — look in
plans/for prior work
Summarize what you've learned before proceeding to questions.
Step 3: Conduct Interview (Context-Informed)
Based on what you read, present recommended defaults and ask only what you can't infer.
Question 1 - Orient Depth + Core Problem (combined):
Based on the spec, here's what I understand:
Problem: {inferred from spec or "I couldn't determine this — please describe"} Recommended depth: {Standard if spec has clear requirements, Light if it's a small enhancement, Deep if the spec mentions unknowns or market concerns}
Does this sound right? Any adjustments to the problem statement or depth?
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.
- 1mo ago First seen · 212 lines · 0 tokens per session scan A b8bda4f501d8
cub:orient is a command published in the GitHub repository lavallee/cub (5 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,451 tokens. 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.