teak: Skill for Claude Code

.agents/skills/workos/SKILL.md

workos is a skill for Claude Code, Codex from praveenjuge/teak. It costs 159 tokens per session (5,993 once invoked), scanned A, a copy of workos, MIT.

A routing guide for WorkOS, a service that provides login, company sign-in, user directories, permissions, and audit records. It tells an agent which WorkOS reference to read before giving URLs, code, or setup advice.

In plain words
What is it for?
It helps implement, debug, or migrate WorkOS features such as AuthKit, SSO, directory sync, permissions, multi-factor authentication, and audit logs.
Why use it?
WorkOS has many products and exact dashboard fields, URLs, and settings matter. This guide reduces the risk of made-up commands or incorrect integration instructions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is praveenjuge/teak's own configuration. It tells Claude Code and Codex how to work on teak 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 teak configures →

Reuse

Borrowing it

Nothing to install: this file belongs to praveenjuge/teak. 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/praveenjuge/teak/main/.agents/skills/workos/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/praveenjuge/teak

Made for: Claude Code, Codex.

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 workos

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/praveenjuge/teak/workos"><img src="https://agentmods.dev/badge/skills/praveenjuge/teak/workos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,993 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 92% copy Near-identical to another mod 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 $0.00159 $0.05993
Opus 5.5 $0.00064 $0.02397
Sonnet 5.5 $0.00032 $0.01199
Haiku 4.5 $0.00016 $0.00599

Measured 13d ago against content hash 2e05fc178126, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workos 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 13d 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.

Origin

This is a copy

92% identical to workos — 136 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/workos/SKILL.md · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WorkOS Skill Router

How to Use

This file is a router, NOT the answer. Before responding to the user:

  1. Match the request to a reference file using Rule 0 and the decision tree below.
  2. You MUST Read the matched reference file with the Read tool before producing any answer, URL, or code. If you have not Read a reference, you have not followed this skill.
  3. Follow the instructions inside the reference (it will tell you which live docs to fetch with WebFetch and which gotchas to avoid).

Exception: Widget requests use the workos-widgets skill via the Skill tool — it has its own multi-framework orchestration.

Guardrails (apply to every response)

These apply regardless of which routing rule fires. They exist because the most common failure mode of past WorkOS agent interactions has been plausibly-shaped fabrication of CLI commands and Dashboard paths.

  • Check for the WorkOS MCP server before reaching for the CLI on workspace-management tasks. If the session has WorkOS MCP tools connected (a server exposing whoami, list_operations, query, and mutate — tool names may carry a client-specific prefix), prefer those tools for reading and changing workspace resources: they already run as the signed-in dashboard user, with no CLI install and no API key. The CLI remains the right surface for bootstrap, seeding, local project config, and diagnostics. The full decision guide is the "Choosing a surface" section of references/workos-management.md.
  • Recover a broken WorkOS MCP connection before relying on it — but never treat MCP setup as a prerequisite for CLI work. When the user asks to set up the WorkOS MCP server, or expects MCP tools that turn out to be missing, unauthenticated, or interrupted during startup, read references/workos-mcp.md first: identify the MCP client and requested configuration scope, and do not modify user-global agent configuration without explicit intent. Authentication that depends on a browser, credential store, or host certificates must be completed in the user's normal host shell. If no MCP server is configured and the user hasn't asked for one, do not divert the request into MCP setup — the CLI path in references/workos-management.md fully supports it.
  • Never invent workos CLI commands. Verify named commands with WORKOS_MODE=agent workos --help --json. Before declaring an operation unsupported, also check WORKOS_MODE=agent workos api ls --json for REST endpoints usable through workos api. Do not assume a create subcommand exists because list/get/delete do, or that a GraphQL operation is a REST endpoint. See references/workos-management.md.
  • Every AuthKit integration must configure and verify application URLs. For setup and migrations, read references/workos-authkit-setup.md alongside the framework or language reference. It covers the redirect destination (not necessarily a server callback handler), Sign-out URI, and Initiate login URI. A build passing is not proof that these settings or flows work.
  • Prefer WORKOS_MODE=agent when invoking the workos CLI from a coding-agent session. The CLI auto-detects most agent environments (CLAUDECODE, CLAUDE_CODE, CURSOR_AGENT, CODEX_SANDBOX, non-TTY), but the explicit env var is more reliable across sandbox configurations. See the WorkOS CLI in Coding-Agent Sessions section below.
  • Never invent Dashboard click-paths. Phrases like "Dashboard > Organizations > X > Roles > Map Groups" or dashboard.workos.com/some/specific/path should not appear unless you have verified them against a docs page you just fetched. The Dashboard UI reorganizes; docs pages are stable. Cite the docs URL and describe the destination conceptually ("the Authorization page", "the directory's settings") instead of committing to a click-path.
  • When the user wants to do something not supported by the CLI, say so plainly. Users are better served by "this isn't in the CLI; here's the docs URL for how to do it" than by a fabricated command that fails. See the "Not in the CLI" section of references/workos-management.md.
  • Prefer docs URLs over prose when writing recipes. If a reference file tells you to cite a specific docs URL, cite it literally; don't paraphrase the URL's slug.

Read the full file on GitHub · 363 lines

Files

What ships with it

49 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 13d ago First seen · 363 lines · 159 tokens per session scan A 2e05fc178126

Subscribe to this mod's changes

workos is a skill published in the GitHub repository praveenjuge/teak (25 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 5,993 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to workos, differing in 136 lines, and is treated as a copy.

Related

Other skills, from other repositories

wegent-knowledge

Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.

wecode-ai/Wegent · 51 tokens

design-mcp-server

Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

cyanheads/obsidian-mcp-server · 62 tokens

add-tool

Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.

cyanheads/obsidian-mcp-server · 35 tokens

api-context

Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.clientCapabilities, ctx.enrich, ctx.content), and when to use each.

cyanheads/obsidian-mcp-server · 84 tokens

api-errors

McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.

cyanheads/obsidian-mcp-server · 54 tokens

api-telemetry

Catalog of OpenTelemetry instrumentation built into framework @cyanheads/mcp-ts-core — spans, metrics, completion logs, env config, runtime caveats, custom instrumentation patterns, and cardinality rules. Use when enabling OTel export, adding custom spans or metrics in services, debugging missing telemetry, looking up…

cyanheads/obsidian-mcp-server · 85 tokens