gantry: Skill for Claude Code

.claude/skills/auth/SKILL.md

auth is a skill for Claude Code from geleynse/gantry. It costs 53 tokens per session (3,225 once invoked), scanned A, original, MIT.

A guide to configuring and debugging Gantry's authentication adapters, which control who can access its server and what they are allowed to do. It covers admin and read-only viewer access.

In plain words
What is it for?
Use it when setting up authentication, investigating 403 errors, controlling dashboard access, or connecting Gantry to token, network, Cloudflare Access, layered, or loopback authentication.
Why use it?
It helps explain unexpected access or forbidden responses and provides the rules for selecting built-in or local custom authentication adapters.

Skill for Claude Code

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

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

Reuse

Borrowing it

Nothing to install: this file belongs to geleynse/gantry. 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/geleynse/gantry/main/.claude/skills/auth/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/geleynse/gantry

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 auth

README.md
[![agentmods](https://agentmods.dev/badge/skills/geleynse/gantry/auth/github.svg)](https://agentmods.dev/skills/geleynse/gantry/auth)
Your own site
<a href="https://agentmods.dev/skills/geleynse/gantry/auth"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/auth/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 auth

Your own site · 80×15
<a href="https://agentmods.dev/skills/geleynse/gantry/auth"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,225 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 $0.00053 $0.03225
Opus 5.5 $0.00021 $0.01290
Sonnet 5.5 $0.00011 $0.00645
Haiku 4.5 $0.00005 $0.00323

Measured 2mo ago against content hash a01213c123b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auth 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 2mo 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/auth/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auth — Gantry Server

Pluggable role-based auth. Two roles only: admin (full access) and viewer (read-only). Full adapter config reference: docs/auth.md. This skill covers adapter internals, route classification, and the frontend gating that the reference doc doesn't.

Adapter factory: server/src/web/auth/index.ts::createAuthAdapter(authConfig)

Built from gantry.json's auth key ({ adapter: string, config?: object }). Resolution:

  • No auth key, or adapter: "loopback" → LoopbackAdapter (the documented default — admin only from 127.0.0.1/::1).
  • adapter string matches a built-in name (switch statement) → that adapter.
  • Anything else → must start with ./ (custom adapter, dynamic import() of a local JS/TS module exporting a default AuthAdapter). Throws if it doesn't start with ./ — this is deliberate, to block arbitrary package imports from gantry.json.

Built-in adapter names in code — more than the docs list. docs/auth.md and server/AGENTS.md document five: none, token, cloudflare-access, local-network, layered (plus the loopback default). The switch statement in index.ts also has two more, undocumented in docs/auth.md:

  • deny (adapters/deny.ts) — authenticate() always returns null (always viewer, never admin, no anonymous admin possible even on MCP/localhost bypass paths that don't apply here). Used internally as a fail-closed fallback concept (see isExternallyAccessible() commentary in index.ts), but is directly selectable via "adapter": "deny" too.
  • domain (adapters/domain.ts) — grants admin by matching the Host header against adminDomains, but only if a cf-access-jwt-assertion header is also present (it doesn't validate the JWT itself, just requires evidence the request passed through Cloudflare's edge). The adapter's own doc comment says it "MUST NOT be used as a standalone auth mechanism" — it's designed to be composed inside another adapter after a real CF JWT check, not selected directly. Doc mismatch: docs/auth.md's layered section describes adminDomains as "an optional hint that annotates which Cloudflare tunnel the admin came through" — but layered.ts's own LayeredConfig comment says adminDomains is "accepted but unused — domain auth requires a standalone domain adapter." The layered adapter's authenticate() never reads adminDomains at all; only localNetworkRanges and Cloudflare fields matter. If you need domain-based gating, wire the domain adapter explicitly (or write a custom one) — layered alone will not do it despite what adminDomains in its config suggests.

Read the full file on GitHub · 81 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. 2mo ago First seen · 81 lines · 53 tokens per session scan A a01213c123b0

Subscribe to this mod's changes

auth is a skill published in the GitHub repository geleynse/gantry (4 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 3,225 once invoked, about $0.0002 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 2026-08-31.

Related

auth compared with skills from other repositories

auth next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
authgeleynse/gantrySkill42mo agoMITA53Claude Code
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2kyesterdayMITA46Claude Code
dev-runtimelangwatch/langwatchSkill5.0kyesterdayApache-2.0A172Claude Code
api-designericrisco/rsc-harnessSkill5032d agoMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill252yesterdayMITA106Claude Code