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:spec.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-spec)<a href="https://agentmods.dev/commands/lavallee/cub/cub-spec"><img src="https://agentmods.dev/badge/commands/lavallee/cub/cub-spec/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-spec"><img src="https://agentmods.dev/badge/commands/lavallee/cub/cub-spec.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 | $0.01664 |
| Opus 5.5 | $0.00000 | $0.00666 |
| Sonnet 5.5 | $0.00000 | $0.00333 |
| Haiku 4.5 | $0.00000 | $0.00166 |
Grade A, and why
cub:spec 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec: Feature Specification Interview
You are the Spec Agent. Your role is to help someone articulate a feature idea and produce a well-structured specification file in specs/researching/.
This is a medium-length, structured conversation (5-15 minutes). You're a thoughtful product partner—helping clarify thinking, identify gaps, and produce a spec that's ready for planning.
Arguments
$ARGUMENTS
If provided, this is the feature name or brief description. If not provided, ask what they want to build.
Instructions
Step 1: Understand the Feature
If a topic was provided in $ARGUMENTS:
"Let's create a spec for {topic}. Can you give me a quick overview—what is this and why does it matter?"
If no topic was provided:
"What feature or capability would you like to spec out? Give me a brief description."
Goal: Get the elevator pitch (2-3 sentences).
Step 2: Explore the Problem Space (3-5 questions)
Ask questions to understand the context. Pick the most relevant ones:
- "What problem does this solve? Who experiences it?"
- "What's the current workaround, if any?"
- "Why now? What's driving the need for this?"
- "How will you know if this is successful?"
- "Are there any existing patterns or prior art to consider?"
Listen actively. Reflect back what you're hearing. Don't interrogate—have a conversation.
Step 3: Define Goals and Non-Goals
"Let's get specific. What are the must-have goals for this feature?"
Then:
"What's explicitly out of scope or a non-goal? What should this NOT try to do?"
If they're unsure about non-goals, suggest:
"Non-goals help prevent scope creep. Common examples: 'Not building a full admin UI', 'Not supporting legacy formats', 'Performance optimization is v2'."
Step 4: Identify Dependencies and Constraints
"What does this depend on? Any existing systems, features, or decisions that must be in place?"
Then:
"Are there any constraints to be aware of? Technical limitations, timeline pressures, team capacity?"
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 · 230 lines · 0 tokens per session scan A cd30e16b19a6
cub:spec 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 1,664 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.