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:stage.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-stage)<a href="https://agentmods.dev/commands/lavallee/cub/cub-stage"><img src="https://agentmods.dev/badge/commands/lavallee/cub/cub-stage.svg" alt="Measured on agentmods" 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 | $0.00494 |
| Opus 5 | $0.00000 | $0.00247 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
cub:stage 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 6d 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.
What it actually says
Stage: Import Plan Tasks
You are executing the cub stage command, which bridges planning and execution by importing tasks from a completed plan into the task backend (beads or JSON).
Arguments
$ARGUMENTS
Instructions
Determine the right command flags from the user's input:
| Input | Command |
|---|---|
| (empty) / "stage" / "import" | cub stage (stages most recent complete plan) |
a plan slug like my-feature |
cub stage <slug> |
a file path ending in .md |
cub stage <path> (stages standalone itemized plan) |
| "list" / "show plans" / "available" | cub stage --list |
| "dry run" / "preview" / "what if" | cub stage --dry-run |
| "verbose" / "details" | cub stage --verbose |
What Stage Does
- Validates the plan is complete (orient, architect, itemize stages done)
- Parses the
itemized-plan.mdfile in the plan directory - Imports epics and tasks into the task backend
- Updates the plan status to STAGED
- Generates context files (
prompt-context.md,agent.md)
Prerequisites
- A plan must be complete (all planning stages finished)
- The
itemized-plan.mdfile must exist - A task backend must be configured (beads or JSON)
Examples
# Stage the most recent complete plan
cub stage
# Stage a specific plan by slug
cub stage my-feature-plan
# Preview what would be staged without importing
cub stage --dry-run
# List all plans ready to be staged
cub stage --list
# Stage a standalone itemized plan file (e.g., from punchlist)
cub stage path/to/itemized-plan.md
# Stage with verbose output
cub stage --verbose
After Staging
Once staging completes successfully:
- Tasks are created in the task backend
- Run
cub runto start executing tasks - Use
cub task readyto see available tasks
Run the command via Bash. If staging fails due to an incomplete plan, suggest running cub plan run <spec> first.
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.
- 6d ago First seen · 66 lines · 0 tokens per session scan A cd7db5c860d7
cub:stage is a command published in the GitHub repository lavallee/cub (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 494 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
rules
You are now working on a project with mandatory coding rules. Execute these steps IMMEDIATELY.
set-tracker
Set the issue tracker for the current project.
ijfw-status
Show IJFW state -- mode, routing, memory, recent activity, codebase index, settings. Use when you want the at-a-glance banner you'd otherwise get at session start.
resume-project
Run resume-project now — Now / Blocked / Next. Not a cheat sheet.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.
go
You are the Project Kickstart agent. Your job is simple: find PRDs, validate them, and execute the full implementation pipeline.