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.
npx agentmods add instructions/kriasoft/oauth-callback/claude-mdgit clone --depth 1 https://github.com/kriasoft/oauth-callbackWhat 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 | $0.00739 | $0.00739 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
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 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 — 71 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/ # Source code
│ ├── index.ts # Main entry - exports getAuthCode(), OAuthError, mcp namespace
│ ├── mcp.ts # MCP SDK exports - browserAuth(), storage, types
│ ├── server.ts # HTTP server for OAuth callbacks
│ ├── errors.ts # OAuthError class and error handling
│ ├── mcp-types.ts # TypeScript interfaces for MCP integration
│ ├── auth/ # Authentication providers
│ │ ├── browser-auth.ts # MCP SDK-compatible OAuth provider
│ │ └── browser-auth.test.ts
│ ├── storage/ # Token storage implementations
│ │ ├── memory.ts # In-memory token store
│ │ └── file.ts # Persistent file-based token store
│ └── utils/ # Utility functions
│ └── token.ts # Token expiry calculations
│
├── templates/ # HTML templates for callback pages
│ ├── success.html # Success page with animated checkmark
│ ├── error.html # Error page for OAuth failures
│ └── build.ts # Template compiler (bundles HTML into TypeScript)
│
├── examples/ # Usage examples
│ ├── demo.ts # Interactive demo with mock OAuth server
│ ├── github.ts # GitHub OAuth integration example
│ └── notion.ts # Notion MCP with Dynamic Client Registration
│
├── dist/ # Build output (generated)
│ ├── index.js # Main bundle
│ ├── index.d.ts # Main TypeScript declarations
│ ├── mcp.js # MCP-specific bundle
│ ├── mcp.d.ts # MCP TypeScript declarations
│ └── ...
│
├── package.json # Project metadata and dependencies
├── tsconfig.json # TypeScript configuration
├── README.md # User documentation
└── CLAUDE.md # This file - AI assistant context
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 First seen · 71 lines · 739 tokens per session scan A 1c759d511072
oauth-callback CLAUDE.md is an instructions file published in the GitHub repository kriasoft/oauth-callback (11 stars, last pushed 7mo ago), licensed MIT. It adds 739 tokens to every session, about $0.0037 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 2026-08-30.
Other instructions, from other repositories
algorand-mcp AGENTS.md
Instructions for GoPlausible/algorand-mcp, covering algorand mcp — agent guide, calling mcp tools, session start, network selection and amounts and decimals.
dsh-mcp-manager AGENTS.md
Instructions for hyqhyq3/dsh-mcp-manager, covering agents.md, layout, architecture rules, commands and conventions.
payload-mcp-oauth CLAUDE.md
Instructions for BrainWeb/payload-mcp-oauth, covering claude.md, project overview, repository structure, commands and install (run once at root).
mcp-sso CLAUDE.md
Instructions for acartag7/mcp-sso, covering claude code session notes (mcp-sso) and repository quality rules.
pixabay-mcp-server CLAUDE.md
Claude Code instructions for hanoak/pixabay-mcp-server, covering claude.md, project overview, tech stack (decided — do not relitigate without discussion), architecture & folder conventions and coding standards.
m365-mcp-server CLAUDE.md
Claude Code instructions for SwamiRama/m365-mcp-server, covering m365 mcp server - project context, projektübersicht, architektur, wichtige dateien and deployment.