boxel: Skill for Claude Code

.claude/skills/catalog-deploy/SKILL.md

catalog-deploy is a skill for Claude Code from cardstack/boxel. It costs 249 tokens per session (2,528 once invoked), scanned A, original, MIT.

A deployment guide for moving boxel-catalog changes through staging and production. It explains which catalog revision each environment receives and how production deployment is started.

In plain words
What is it for?
Use it to deploy catalog changes, choose the correct production workflow, and understand the link between catalog and application releases.
Why use it?
It removes uncertainty about why a merged catalog change may appear in staging but not production, and helps keep catalog files matched with the boxel code that uses them.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is cardstack/boxel's own configuration. It tells Claude Code how to work on boxel 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 boxel configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is GH_TOKEN=$(gh auth token) node packages/catalog/scripts/catalog-deploy-check.ts \.

Reuse

Borrowing it

Nothing to install: this file belongs to cardstack/boxel. 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/cardstack/boxel/main/.claude/skills/catalog-deploy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cardstack/boxel

Made for: Claude Code.

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 catalog-deploy

README.md
[![agentmods](https://agentmods.dev/badge/skills/cardstack/boxel/catalog-deploy/github.svg)](https://agentmods.dev/skills/cardstack/boxel/catalog-deploy)
Your own site
<a href="https://agentmods.dev/skills/cardstack/boxel/catalog-deploy"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/catalog-deploy/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 catalog-deploy

Your own site · 80×15
<a href="https://agentmods.dev/skills/cardstack/boxel/catalog-deploy"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/catalog-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 249 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,528 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.
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 $0.00249 $0.02528
Opus 5.5 $0.00100 $0.01011
Sonnet 5.5 $0.00050 $0.00506
Haiku 4.5 $0.00025 $0.00253

Measured 5d ago against content hash 4667d055a537, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

catalog-deploy 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.

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.

.claude/skills/catalog-deploy/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploying the catalog

The catalog realm (/catalog/) serves boxel-catalog's files, and its cards import the boxel platform the environment runs. A catalog change that needs boxel code breaks an environment whose boxel doesn't have that code yet. So each environment gets catalog changes on its own schedule:

Environment Its boxel Its catalog
staging boxel main, deployed on every merge catalog main, synced on every catalog merge (boxel-catalog's Deploy to staging, sync-to-workspace.yml)
production whatever the last Manual Deploy [boxel] shipped only what boxel-catalog's Deploy to production (deploy-production.yml) deploys

Two ways a catalog change reaches production

  • In lockstep with boxel. Manual Deploy [boxel] to production deploys the catalog revision the deployed boxel commit pins (revision in packages/catalog/test-subset.json), which boxel's tests ran against. It does this twice, through packages/catalog/scripts/dispatch-catalog-deploy.sh, waiting for each run:
    • Before the release (Deploy the pinned catalog before the release). The check runs against the boxel production still runs, so this ships the catalog changes the new boxel needs (a boxel pull request that says Merges after: cardstack/boxel-catalog#N), and refuses when the range has a catalog change that needs the new boxel. A refusal or failure here is only a notice and doesn't hold back the release.
    • After the release (Deploy the pinned catalog after the release). This ships the rest, such as catalog changes pinned by the boxel pull request that brings the code they need. If it fails or refuses, the job goes red: production then runs the new boxel against an older catalog.

Read the full file on GitHub · 101 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. 5d ago First seen · 101 lines · 249 tokens per session scan A 4667d055a537

Subscribe to this mod's changes

catalog-deploy is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 249 tokens to every session and 2,528 once invoked, about $0.0010 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 2026-10-21.