boxel: Skill for Claude Code

.claude/skills/outbound-guard/SKILL.md

outbound-guard is a skill for Claude Code from cardstack/boxel. It costs 404 tokens per session (5,853 once invoked), scanned C, original, MIT.

A guide to the server component that controls requests carrying stored credentials to outside services. It explains which destinations and redirects are refused and how to diagnose those refusals.

In plain words
What is it for?
Use it when debugging outbound requests, redirects, URL substitutions, OpenRouter calls, or card operations that contact external vendors.
Why use it?
It prevents credentials from being sent to unsafe destinations, while making rejected requests easier to investigate.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/tail-logs.sh --env production --service realm-server --filter 'key=system:https://openrouter.ai/api/v1' --since 1d --no-follow --confirm.

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/outbound-guard/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 outbound-guard

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cardstack/boxel/outbound-guard"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/outbound-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 404 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,853 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00404 $0.05853
Opus 5.5 $0.00162 $0.02341
Sonnet 5.5 $0.00081 $0.01171
Haiku 4.5 $0.00040 $0.00585

Measured 5d ago against content hash f37860b3f4c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

outbound-guard scanned grade C with 1 finding 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.

Cloud metadata endpointhighServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

| `address` | the host is, or resolves to, a non-public address: private, loopback, link-local, CGNAT, multicast, reserved, IPv4-mapped/embedded forms of those, and the metadata addresses `169.254.169.254` / `fd00:ec2::2
.claude/skills/outbound-guard/SKILL.md · 412 lines

How it starts

The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Outbound guard (operators)

Every realm-server call that carries a stored credential to an outside vendor goes through outboundFetch in packages/realm-server/lib/outbound/client.ts. Today that is POST /_request-forward (including streamed calls), POST /_openrouter/chat/completions, the generation-cost lookup either of them makes when a response carried a generation id but no inline cost (OpenRouterCreditStrategy in lib/credit-strategies.ts), and every callApi card operation (lib/outbound/call-api-sender.ts; see the call-api skill). A callApi carries no credential: its credentials are substitutions, filled into the request after the destination check and never followed across a redirect to another origin. A substitution may not change the URL's origin, and one filled into the path stays within its segment: a value holding / or \, or one the URL would resolve away as a dot segment, is refused invalid-url (502) before anything is sent. The guard is always on, in every environment; local development gets a short allowlist, never an off switch.

What it refuses

Refusal When Caller sees
scheme the URL (or a redirect hop) is not https:, and its host is not on the development allowlist 502 Destination refused: Only https URLs …
address the host is, or resolves to, a non-public address: private, loopback, link-local, CGNAT, multicast, reserved, IPv4-mapped/embedded forms of those, and the metadata addresses 169.254.169.254 / fd00:ec2::254 502 Destination refused: … private or reserved
forbidden-header a header named X-Boxel-* in the forwarded headers 400, before any credit slot is taken
too-many-redirects more than 5 redirect hops 502
timeout (connect/total) no connection in 10 s, or the whole exchange (every hop and the body) not done in 10 min 504; mid-stream, an SSE error frame then [DONE]

Read the full file on GitHub · 412 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 · 412 lines · 404 tokens per session scan C f37860b3f4c5

Subscribe to this mod's changes

outbound-guard is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 404 tokens to every session and 5,853 once invoked, about $0.0016 per session on Opus 5.5. A static security scan graded it C with 1 finding (cloud metadata endpoint). 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

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens

migrate-segw-to-rap

Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…

arc-mcp/arc-1 · 106 tokens

api-design

Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency — emitted as OpenAPI 3.1. NOT implementing the endpoints (that is fastapi/nestjs/go/nodejs), NOT auth hardening (that is secure-coding), NOT…

ericrisco/rsc-harness · 105 tokens