workspace-admin-mcp: Instructions file for Codex

AGENTS.md

workspace-admin-mcp AGENTS.md is an instructions file for Codex, OpenCode from pizzacrustreviewer/workspace-admin-mcp. It costs 768 tokens per session, scanned A, original, MIT.

A repository instruction guide for a narrowly scoped Google Workspace tool server. It defines boundaries between authentication, agent-to-tool communication, routing, authorization, and monitoring.

In plain words
What is it for?
Use it when changing the workspace administration server or reviewing its security behavior. It provides engineering rules for authorization, Google access scopes, retries, and audit identity.
Why use it?
It helps developers and coding agents avoid unsafe design choices, such as treating tool allowlists as a complete security boundary or forwarding credentials incorrectly.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is pizzacrustreviewer/workspace-admin-mcp's own configuration. It tells Codex and OpenCode how to work on workspace-admin-mcp 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 workspace-admin-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pizzacrustreviewer/workspace-admin-mcp. 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/pizzacrustreviewer/workspace-admin-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/pizzacrustreviewer/workspace-admin-mcp

Made for: Codex, OpenCode.

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 workspace-admin-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pizzacrustreviewer/workspace-admin-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/pizzacrustreviewer/workspace-admin-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pizzacrustreviewer/workspace-admin-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/pizzacrustreviewer/workspace-admin-mcp/agents-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 workspace-admin-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pizzacrustreviewer/workspace-admin-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/pizzacrustreviewer/workspace-admin-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 768 This file is loaded in full into every session.
When invoked 768 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 $0.00768 $0.00768
Opus 5.5 $0.00307 $0.00307
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured yesterday against content hash b2ac030e992f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-23, from the pricing page.

Security

Grade A, and why

workspace-admin-mcp AGENTS.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.

AGENTS.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Agent Guide

This repository implements a narrowly scoped Google Workspace MCP tool boundary.

Architecture Contract

Keep these responsibilities distinct:

OAuth/OIDC        authority and delegated identity
A2A               agent-to-agent interoperability
MCP               agent-to-tool interoperability
Gateway           routing, quotas, and coarse policy
OpenTelemetry     cross-boundary observability
  • Do not add A2A unless this server becomes an independently discoverable agent.
  • Gateway authorization is defense in depth. Every tool must enforce policy inside the server.
  • Trace context is correlation data, never an authorization input.
  • Never pass an inbound MCP token through to Google.
  • Derive outbound Google scopes from the final exposed tool set.
  • Stateless transport does not make an operation safe to retry.
  • Tool allowlists are not a sandbox. Never claim agent containment when the agent host can read Google credentials or invoke their signing identity.
  • A single-user audit selector identifies the actor, not necessarily the affected user. Preserve that distinction in tool names, outputs, and findings.
  • Treat missing evidence as unknown, not safe. Traces are not a durable audit log.
  • Use synthetic data by default until a separate test tenant is explicitly available.

Privileged Changes

Do not add direct mutation tools. Use:

inspect -> propose structured diff -> policy check -> approve exact diff -> execute -> verify

Approval must bind the principal, tenant, exact diff hash, operation ID, and expiry. Execution must reject changed, replayed, or expired proposals.

Current Boundary

Version 0.2 provides synthetic-only local stdio and an experimental authenticated HTTP service. It supports scoped discovery, structured pages, deterministic review, redacted logs, and OpenTelemetry spans through the Google adapter. HTTP verifies JWT access tokens per request and intersects scopes with static server policy.

Protected-resource metadata is implemented. Real IdP/Google integration and isolated deployment remain unverified. Per-investigation grants, durable principal audit, gateway configuration, token exchange, durable idempotency, and writes are absent. Never restore Google credentials to the stdio/client setup.

Read the full file on GitHub · 82 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. yesterday First seen · 82 lines · 768 tokens per session scan A b2ac030e992f

Subscribe to this mod's changes

workspace-admin-mcp AGENTS.md is an instructions file published in the GitHub repository pizzacrustreviewer/workspace-admin-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 768 tokens to every session, about $0.0031 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 2026-09-22.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,406 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, repository design references, quickstart — add a new integration in 5 steps and integration architecture.

github/spec-kit · 7,326 tokens

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.

vercel/next.js · 6,923 tokens

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.

openai/codex · 5,153 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens