Borrowing it
Nothing to install: this file belongs to feedback-loop-ai/mcp-ory-kratos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/feedback-loop-ai/mcp-ory-kratos/main/CLAUDE.mdgit clone --depth 1 https://github.com/feedback-loop-ai/mcp-ory-kratosWrote 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.
[](https://agentmods.dev/instructions/feedback-loop-ai/mcp-ory-kratos/claude-md)<a href="https://agentmods.dev/instructions/feedback-loop-ai/mcp-ory-kratos/claude-md"><img src="https://agentmods.dev/badge/instructions/feedback-loop-ai/mcp-ory-kratos/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02340 | $0.02340 |
| Opus 5 | $0.01170 | $0.01170 |
| Sonnet 5 | $0.00468 | $0.00468 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
mcp-ory-kratos CLAUDE.md 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
MCP (Model Context Protocol) server for Ory Kratos - an open-source identity and user management system.
Build & Development Commands
# Start MCP server
bun run start
# Lint (Biome)
bun run lint
bun run lint:fix # Auto-fix issues
# Type check
bun x tsc --noEmit
# Type check src + tests
bun run typecheck
# Unit tests only (CI-safe, no external dependencies, with coverage)
bun run test:unit
# Integration tests against a local Kratos v26.2.0
docker compose up -d --wait && bun run test:api
# All tests / watch mode (requires Kratos - see .env.test.local.example)
bun run test
bun run test:watch
# Dependency audit
bun run audit
CI/CD
GitHub Actions CI runs on every push and PR:
- Lint:
bun run lint(Biome) - Type Check:
bun x tsc --noEmit - Audit:
bun audit --audit-level=high - Test: Unit tests with coverage (tests/unit/)
- Integration: Starts Kratos v26.2.0 via
docker-compose.yml(config intests/kratos/) and runsbun run test:api
Test organization:
tests/unit/- Hermetic unit tests (in-memory MCP client, stubbed Kratos)tests/api/- Integration tests against a real Kratos (docker compose locally and in CI)
Architecture
Stateless proxy from MCP to the Kratos Admin API. Layers, bottom up:
src/config.ts-loadConfig(env)validatesKRATOS_*env vars into aConfig(URL, auth, timeout, toolsets, runtime flags).src/kratos/client.ts-createKratosClients(config)builds@ory/kratos-clientIdentityApi/CourierApi/MetadataApiplus a rawhttp.getfor endpoints the SDK cannot reach. Strips trailing/and a trailing/adminfrom the base URL (the SDK adds/adminitself).kratos/pagination.tsextractsnextPageTokenfrom Link headers;kratos/types.tsholdsCREDENTIAL_TYPES(7 login types),ALL_CREDENTIAL_TYPES(11) andredactCredentials.src/tools/define.ts-defineTool(ctx, def)is the single registration path. It wrapsMcpServer.registerToolwith logging/timing,mapError(src/errors/mapper.ts),structuredContentwhen anoutputSchemais given, annotations (READ_ONLY,CREATE,UPDATE,UPDATE_IDEMPOTENT,DESTRUCTIVEpresets), toolset gating and read-only gating (disabled tools are hidden fromtools/list), and aconfirm(message)helper that uses MCP elicitation fordestructiveHinttools (returnsCANCELLEDwhen declined).src/tools/*.ts- oneregisterXxxTools(ctx)per toolset (identity, session, courier, recovery, health, analytics). Zod input/output schemas live insrc/schemas/tools.ts.src/resources/schemas.ts- resourceskratos://schemas,kratos://schemas/{schema_id}(ResourceTemplate with list + completion) andkratos://config/connection.src/server.ts-createServer(config, clients)builds theMcpServer(instructions, logging bridge to the client,logging/setLevel) and registers every toolset and the resources.src/index.ts- CLI entrypoint: load config, create clients, create server, connect stdio.
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.
- yesterday Changed · +46 lines · +1,349 tokens per session 9cbd81aec895
- 8d ago First seen · 69 lines · 991 tokens per session scan A bfb224f00b35
mcp-ory-kratos CLAUDE.md is an instructions file published in the GitHub repository feedback-loop-ai/mcp-ory-kratos (1 stars, last pushed 2d ago), licensed MIT. It adds 2,340 tokens to every session, about $0.0117 per session on Opus 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.