boxel: Skill for Claude Code

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

catalog-pairing is a skill for Claude Code from cardstack/boxel. It costs 326 tokens per session (3,575 once invoked), scanned A, original, MIT.

A guide to pairing related pull requests in the boxel and boxel-catalog repositories. A pull request is a proposed change for review before it is merged.

In plain words
What is it for?
Use it to mark matching pull requests, decide which change merges first, and coordinate code changes with catalog updates.
Why use it?
It prevents dependent changes from being merged in the wrong order or without the matching change in the other repository.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions subagents.

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 →

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-pairing/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-pairing

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cardstack/boxel/catalog-pairing"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/catalog-pairing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 326 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,575 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 $0.00326 $0.03575
Opus 5.5 $0.00130 $0.01430
Sonnet 5.5 $0.00065 $0.00715
Haiku 4.5 $0.00033 $0.00358

Measured 5d ago against content hash 1c8c16428612, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

catalog-pairing 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-pairing/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pairing boxel and boxel-catalog pull requests

This repo's PreToolUse hook (.claude/hooks/require-skill.mjs) refuses to open or edit a boxel-catalog pull request, or to write a Merges before: / Merges after: line into any pull request's description, through gh pr or the GitHub MCP tools, until the session or subagent has loaded this skill.

boxel-catalog's cards import boxel (host tools, @cardstack/base, runtime types), and boxel's tests use some catalog definitions. So a change in one repository can need a change in the other, and the two pull requests have to be checked together and merged in the right order. Each pull request says which pull request it pairs with in its description, and the checks in both repositories read that.

When a change needs a pair

  • A boxel change the catalog has to follow. Renaming or removing a host tool or command (@cardstack/boxel-host/tools/*), a base export, a field or a type that catalog cards import, or tightening a type or lint rule they trip. The boxel pull request merges first, and the catalog pull request that adapts the cards merges right after it. The boxel pull request also pins the catalog pull request's head (see The pin covers the whole catalog).
  • A catalog change boxel's tests need. A new or changed definition in the catalog test subset (the catalog-test-subset skill). The catalog pull request merges first, and the boxel pull request that re-pins and tests it merges after.
  • Both at once: the three-PR flow. A catalog definition that needs new platform code, and whose boxel tests need the new definition. Platform pull request A merges, then catalog pull request C, then boxel pull request B, which re-pins and tests. C is tested against B's head, and that head needs A's platform code. So B carries A by merging A's branch into it and following A until A merges. B may target main with A merged in, or be stacked on A (below) and be retargeted to main once A merges. Stacked, B can't pass the catalog-main gate as a Merges before side until it's retargeted, since merging it lands it on A's branch, not main.

Read the full file on GitHub · 88 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 · 88 lines · 326 tokens per session scan A 1c8c16428612

Subscribe to this mod's changes

catalog-pairing is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 326 tokens to every session and 3,575 once invoked, about $0.0013 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.