agentmods.dev

idpsim

idpsim is a skill for Claude Code from langwatch/langwatch. It costs 118 tokens per session (2,520 once invoked), scanned A, original, Apache-2.0.

A local stand-in for an identity provider, the service that signs users in and supplies account data to other applications. It supports OIDC and SAML sign-in, SCIM user provisioning, and domain ownership checks.

In plain words
What is it for?
Use it to test SSO login, user provisioning, security keys, and domain verification against a local service.
Why use it?
It lets you test enterprise sign-in without creating an account with a real identity provider or sending requests outside your computer.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

not rated 5.0krepo +10 changed 14d ago A scan 118 tokens original Apache-2.0

Good fit Use it to test SSO login, user provisioning, security keys, and domain verification against a local service.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/langwatch/langwatch/idpsim
View source ↗ langwatch/langwatch langwatch.ai
About the project

LangWatch is a platform for testing, evaluating, and monitoring LLM-powered agents before release and in production. Teams use it to run agent simulations, trace and evaluate behavior, improve prompts and models, review failures, and manage provider costs and governance.

langwatch/langwatch · 4,993 stars · on GitHub · langwatch.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add langwatch/langwatch --skill idpsim
Clone the repo
git clone --depth 1 https://github.com/langwatch/langwatch

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 idpsim

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/langwatch/langwatch/idpsim"><img src="https://agentmods.dev/badge/skills/langwatch/langwatch/idpsim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,520 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 $0.00118 $0.02520
Opus 5.5 $0.00047 $0.01008
Sonnet 5.5 $0.00024 $0.00504
Haiku 4.5 $0.00012 $0.00252

Measured 14d ago against content hash 64cf8293f1be, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

idpsim 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 14d 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/idpsim/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

idpsim

One Go process playing the customer's IdP across independent tenants (/t/1 to /t/N): an OIDC provider, a SAML identity provider, a SCIM 2.0 directory (it also pushes at LangWatch's SCIM endpoint) and a fake domain owner (acme<n>.test, DNS TXT and a well-known token). Permissive by design: never expose it. Code: services/sims/idpsim (the README there is the full reference), console apps/sims/src/idp (ADR-160).

Run it

  • On by default in haven (haven up -idp turns it off). Runs in the go lane by default (see sims).
  • Console: https://idp.<slug>.langwatch.localhost; tenant pages at /t/<n>/. haven status shows the loopback port and the DNS port (default :15353).
  • The overlay sets LANGWATCH_IDPSIM_URL, SSO_TRUSTED_IDP_ORIGINS and SSO_DOMAIN_PROOF_DNS_SERVERS (tools/thuishaven/domain/overlay.go).
  • State persists under haven's home per slug (IDPSIM_DATA_DIR), so a restart keeps registered apps, users and keys. A direct run with no data dir is in memory.
  • Only the simulator, no stack: haven simulator idp [--tenants <n>]. Standalone from source: make service svc=idpsim (:5565). A wider range: IDPSIM_TENANTS=20.
  • haven sim idp status --json [--stack <slug>] reads a running stack's identity-provider summaries.

Use a tenant

  • OIDC: issuer <base>/t/<n>, discovery at /.well-known/openid-configuration. Register the application on the tenant page (or POST /control/t/<n>/apps) to get client id and secret; an unknown client id is still accepted with anything.
  • SAML: sign-in <base>/t/<n>/saml/sso, metadata <base>/t/<n>/saml/metadata.
  • Zero-click login in a test: login_hint=<email>. Seeded users per tenant: admin@acme<n>.test, member@acme<n>.test.
  • Social sign-in (Google, GitHub, GitLab, Microsoft): +idp points GOOGLE_SIGN_IN_BASE, GITHUB_SIGN_IN_BASE, GITLAB_SIGN_IN_BASE and MICROSOFT_SIGN_IN_BASE at tenant 1's /t/1/social/<provider>. Set AUTH_PROVIDER to a non-email provider and any <PROVIDER>_CLIENT_ID/_SECRET (idpsim accepts anything), then press the provider's button; [email protected] skips the picker. Read social.<provider>.* in the activity feed.
  • Activity (every authorize, token, assertion, SCIM call with an outcome and a reason):
  • On an IS_SAAS stack also set LOCAL_PASSWORDS_ENABLED=on, or admin password sign-in is refused (EMAIL_PASSWORD_DISABLED). GET /control/t/<n>/activity, or the tenant page's activity tab. Read it first when a login fails: it says whether the request even arrived.

Read the full file on GitHub · 113 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. 14d ago Changed 64cf8293f1be
  2. 15d ago First seen · 113 lines · 118 tokens per session scan A 125bccde99c4

Subscribe to this mod's changes

idpsim is a skill published in the GitHub repository langwatch/langwatch (4,993 stars, last pushed today), licensed Apache-2.0. It adds 118 tokens to every session and 2,520 once invoked, about $0.0005 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 2026-10-13.

Analytics and metricsE2E testingEvaluationLLMTestingaidatasetsgpt
Related

Other skills, from other repositories

smoke-test

Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.

Skyvern-AI/skyvern · 50 tokens

local-test

Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation.

suyoumo/ClawProBench · 22 tokens

ui-data-testid

Add stable data-testid attributes when a new or refactored UI flow needs reliable unit or E2E selectors. Use for interactive React/TSX views, menus, or test-driven UI work; do not add selectors to static markup without a test or automation need.

dtyq/magic · 60 tokens

web-ui-test

Test the IronClaw web UI using the Claude for Chrome browser extension.

suyoumo/ClawProBench · 19 tokens

tdd-workflow

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

affaan-m/ECC · 43 tokens

reproduce-bug

Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…

googleapis/mcp-toolbox · 130 tokens