boxel: Skill for Claude Code

.claude/skills/system-keys/SKILL.md

system-keys is a skill for Claude Code from cardstack/boxel. It costs 217 tokens per session (2,988 once invoked), scanned A, original, MIT.

A command-line guide for managing system-held vendor credentials on a Boxel realm server. A realm server is the service that hosts and processes Boxel data; these credentials are stored and forwarded for outside services such as OpenRouter.

In plain words
What is it for?
Use it to list, inspect, add, replace, or delete system keys on a realm server.
Why use it?
It prevents secrets from being changed with unsafe database commands and preserves the server's protected storage and audit trail. It also explains which credentials belong to the platform rather than individual users.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/system-keys/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 system-keys

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cardstack/boxel/system-keys"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/system-keys.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 217 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,988 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 $0.00217 $0.02988
Opus 5.5 $0.00087 $0.01195
Sonnet 5.5 $0.00043 $0.00598
Haiku 4.5 $0.00022 $0.00299

Measured 5d ago against content hash e5c8d9affcee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

system-keys 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/system-keys/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System keys (operators)

A system key is a key the platform itself holds for an outside vendor, such as OpenRouter's. Each one is a row in proxy_endpoints: a destination URL, how the key is attached, how calls are charged, and the key, sealed at rest. _request-forward (and the OpenRouter passthrough) attaches the key to any forwarded request whose URL has the destination's origin and falls under its path. System keys belong to the platform, not to any user: they are managed by developers who hold the environment's realm secret seed, and no user session, however privileged, can reach them.

Never add or change a row with a hand-written SQL statement: the table holds no plain-text key, so SQL can't seal one, and the change would leave no audit entry. Use the command.

The command

export BOXEL_REALM_SECRET_SEED=…   # or let the command prompt for it
boxel realm-server keys list    --realm-server <url>
boxel realm-server keys show    --realm-server <url> (--destination <url> | --id <id>)
boxel realm-server keys add     --realm-server <url> --destination <url> \
                                --credit-strategy openrouter|none \
                                [--auth header|url-parameter] [--param-name <name>] \
                                [--streaming] [--stdin | --key-file <path>] [--note <text>]
boxel realm-server keys replace --realm-server <url> (--destination <url> | --id <id>) \
                                [--stdin | --key-file <path>] [--note <text>]
boxel realm-server keys delete  --realm-server <url> (--destination <url> | --id <id>) [--note <text>]

Every command takes --json. boxel realm-server is left out of the CLI's general help (and out of boxel-skills); boxel realm-server keys --help shows the commands.

  • --realm-server is the realm server's own URL: https://localhost:4201 locally, the environment's realm server URL elsewhere. It must be https: (plain http: only for localhost, 127.0.0.1 or [::1]), and the command refuses to follow a redirect, so neither the token nor a value crosses the network in clear text or lands on another origin. Its origin must be the one the server knows itself by (its --serverURL): the token is signed for that origin alone.
  • add refuses a destination that already has a key (409); use replace. It also refuses (409) a destination that overlaps an existing one, on the same origin with one path under the other: a request under both would match either, and which key it got would depend on row order. It keeps the destination and settings and swaps only the value. To change a destination or its settings, delete it and add it again.
  • --destination names a key as the server stores it: the URL as the URL parser spells it (https://VENDOR.test is https://vendor.test/). A destination is an https: URL with no credentials, query string or fragment. Plain http: is accepted only for a host on the outbound client's development allowlist (OUTBOUND_DEV_ALLOWLIST, empty on a deployed server), the one case where the proxy sends a key over http.
  • --auth header (the default) sends the key as Authorization: Bearer <key>. With --param-name, it goes in that header instead, still as Bearer <key>: a vendor that wants the bare key in a custom header can't be served. --auth url-parameter sends it as the query parameter --param-name (default key).
  • --credit-strategy openrouter charges the caller's credits from OpenRouter's reported cost; none charges nothing.

Read the full file on GitHub · 208 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 · 208 lines · 217 tokens per session scan A e5c8d9affcee

Subscribe to this mod's changes

system-keys is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 217 tokens to every session and 2,988 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.

microsoft/vscode · 53 tokens