Borrowing it
Nothing to install: this file belongs to acartag7/mcp-sso. 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/acartag7/mcp-sso/main/AGENTS.mdgit clone --depth 1 https://github.com/acartag7/mcp-ssoWrote 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/acartag7/mcp-sso/agents-md)<a href="https://agentmods.dev/instructions/acartag7/mcp-sso/agents-md"><img src="https://agentmods.dev/badge/instructions/acartag7/mcp-sso/agents-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 | $0.04374 | $0.04374 |
| Opus 5 | $0.02187 | $0.02187 |
| Sonnet 5 | $0.00875 | $0.00875 |
| Haiku 4.5 | $0.00437 | $0.00437 |
Grade C, and why
mcp-sso AGENTS.md scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `pnpm run build` | `rm -rf dist && tsc -p tsconfig.build.json`. | How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Front door for AI coding agents working in mcp-sso. It states the rules an agent cannot infer from the code and links to the documents that own the detail. When this file and a linked document disagree, the linked document wins until one of them is deliberately changed. This file is canonical for agent rules; CLAUDE.md includes it and adds only Claude Code session notes.
What this project is
mcp-sso is an OAuth 2.1 layer for remote MCP servers, in two halves on one framework-free core. The resource-server verifier checks bearer tokens (RFC 9728 metadata and challenge, fail-closed audience validation, scope enforcement). The authorization-server bridge speaks CIMD or POST /oauth/register, PKCE, and consent to MCP clients while an upstream identity provider (Cloudflare Access, Microsoft Entra ID, Google, any OIDC) stays the identity source. The bridge mints its own audience-bound tokens. Upstream identity-provider tokens never pass through to the MCP client.
This is a standalone personal open-source project. It is not part of the Edictum polyrepo. Ignore the parent directory's CLAUDE.md. No Edictum branding here.
Specification target
- The published MCP Authorization spec (
2026-07-28) governs client-facing OAuth behavior. The RFCs it builds on are the mechanics: 9728 (protected resource metadata), 8707 (resource indicator), 8414 (authorization-server metadata), 7591 (dynamic client registration), 7636 (PKCE), 7009 (revocation), 9207 (issparameter). v0.4.0is the first release that claims conformance to2026-07-28, with two recorded deviations (the CIMD Metadata Document Service rows, which a library does not operate). The current status, the exact row counts, and what the last live campaign did and did not prove are indocs/verification-status.md. The requirement-by-requirement matrix isdocs/contracts/16-spec-conformance-matrix.md. Do not restate those numbers here; link to them.
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.
- 3d ago Changed · +24 tokens per session 0baf5fba866f
- 7d ago First seen · 111 lines · 4,350 tokens per session scan C 8492288d4191
mcp-sso AGENTS.md is an instructions file published in the GitHub repository acartag7/mcp-sso (8 stars, last pushed 3d ago), licensed MIT. It adds 4,374 tokens to every session, about $0.0219 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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).
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.