oauth-callback: Instructions file for Claude Code

CLAUDE.md

oauth-callback CLAUDE.md is an instructions file for Claude Code from kriasoft/oauth-callback. It costs 570 tokens per session, scanned A, original, MIT.

Project instructions for the oauth-callback TypeScript package, which handles OAuth sign-in callbacks and related token storage. OAuth is a standard way for an application to obtain permission to use another service on a user's behalf.

In plain words
What is it for?
Use it when working on browser-based authentication, HTTP callback handling, token expiry, in-memory or file-based token storage, and integrations with the Model Context Protocol SDK.
Why use it?
It gives contributors the project's documented structure, modules, exports, design decisions, and specifications so changes follow the existing codebase.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is kriasoft/oauth-callback's own configuration. It tells Claude Code how to work on oauth-callback 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 oauth-callback configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kriasoft/oauth-callback. 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/kriasoft/oauth-callback/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kriasoft/oauth-callback

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 oauth-callback CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kriasoft/oauth-callback/claude-md/github.svg)](https://agentmods.dev/instructions/kriasoft/oauth-callback/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kriasoft/oauth-callback/claude-md"><img src="https://agentmods.dev/badge/instructions/kriasoft/oauth-callback/claude-md/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 oauth-callback CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kriasoft/oauth-callback/claude-md"><img src="https://agentmods.dev/badge/instructions/kriasoft/oauth-callback/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 570 This file is loaded in full into every session.
When invoked 570 The same file — it is already loaded in full.
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 $0.00570 $0.00570
Opus 5.5 $0.00228 $0.00228
Sonnet 5.5 $0.00114 $0.00114
Haiku 4.5 $0.00057 $0.00057

Measured 1mo ago against content hash bc7df0e27c0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oauth-callback 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 1mo 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.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OAuth Callback Project Guide

Documentation

ADRs (docs/adr/NNN-slug.md): Architectural decisions (reference as ADR-NNN)
SPECs (docs/specs/slug.md): Design specifications (reference as SPEC-slug)

Project Structure

oauth-callback/
├── src/
│   ├── index.ts             # Root exports: getAuthCode, OAuthCallbackError, types
│   ├── get-auth-code.ts     # getAuthCode(), URL validation, lifecycle (ADR-004, ADR-007)
│   ├── loopback.ts          # Redirect URI parsing, node:http callback listener, pages (ADR-008)
│   ├── launch.ts            # Default launcher (lazy `open` chunk)
│   └── mcp/
│       ├── index.ts         # /mcp exports: browserAuth, fileStore, types
│       ├── browser-auth.ts  # MCP SDK provider, connect(), flow ownership (ADR-006)
│       ├── credential-store.ts # CredentialStore + stored document format (ADR-005)
│       └── file-store.ts    # fileStore(absolutePath)
├── test/                    # bun:test suites, mock MCP/AS server, runtime smoke test
├── scripts/build.ts         # Split bundle (root, /mcp, lazy launcher chunk)
├── examples/                # demo (mock AS), GitHub, Notion MCP
└── docs/                    # VitePress site, ADRs, migration guide

Module Organization

Main Export (oauth-callback)

  • getAuthCode(authorization, options?) - URL or builder form; resolves { code, redirectUri, params }
  • OAuthCallbackError - error callback from the authorization server
  • Core never imports MCP code

MCP Export (oauth-callback/mcp)

  • browserAuth() - OAuthClientProvider + connect(client) + completeAuthorization(transport)
  • fileStore(path) - persistent CredentialStore
  • Types: BrowserAuth, BrowserAuthOptions, CredentialStore (SDK types are never re-exported)

Key Constraints

  • Design Philosophy: Prioritize ideal design over backward compatibility
  • Runtime: Always use Bun (not Node.js/NPM). Bun auto-loads .env files
  • MCP SDK: @modelcontextprotocol/client 2.x (optional peer); OAuth implementation in node_modules/@modelcontextprotocol/client/dist/index.mjs (auth, authInternal), typings in dist/index.d.mts
  • Zero runtime dependencies: open is a devDependency bundled into a lazy chunk

Read the full file on GitHub · 48 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. 1mo ago Changed · -23 lines · -169 tokens per session bc7df0e27c0e
  2. 1mo ago First seen · 71 lines · 739 tokens per session scan A 1c759d511072

Subscribe to this mod's changes

oauth-callback CLAUDE.md is an instructions file published in the GitHub repository kriasoft/oauth-callback (12 stars, last pushed 9d ago), licensed MIT. It adds 570 tokens to every session, about $0.0023 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 2026-08-30.

Related

Other instructions, from other repositories