gdoc-mcp: Instructions file for Codex

AGENTS.md

gdoc-mcp AGENTS.md is an instructions file for Codex, OpenCode from alejoacelas/gdoc-mcp. It costs 464 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions for developing and publishing projects in the gdoc-mcp workspace. AGENTS.md is a file that tells coding agents how to work in a repository.

In plain words
What is it for?
Use it when organising related Git repositories, creating or publishing a project, editing READMEs, or working with local macOS apps.
Why use it?
It gives the agent consistent rules for repository layout, commits, publishing, README writing, and local macOS applications.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alejoacelas/gdoc-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/alejoacelas/gdoc-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 464 This file is loaded in full into every session.
When invoked 464 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 $0.00464 $0.00464
Opus 5.5 $0.00186 $0.00186
Sonnet 5.5 $0.00093 $0.00093
Haiku 4.5 $0.00046 $0.00046

Measured 1mo ago against content hash ea9095a29a30, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gdoc-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 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.

AGENTS.md · 46 lines

What it actually says

Dev Workspace

  • This workspace holds software the user relies on frequently. Build it to last, not as throwaway experiments.
  • Group related projects under an ordinary shared-function folder whose README indexes them; do not also use that folder as a project repo.
  • Keep each project in its own Git repo with its own GitHub remote, including nested projects.
  • Commit project work inside its project repo; keep shared workspace config in dotfiles.
  • Push after committing.
  • Keep changes small.

Publishing a project

  • Create the GitHub remote if it doesn't exist.
  • Use a short, clean repo name.
  • Make the repo public unless the global privacy rules require a private repo.

READMEs

  • Put real effort into the README.
  • Keep it short — write it like a WhatsApp or Slack message, straight to the point.
  • If it can be said in one sentence, don't use two.
  • When the user's prompt has its own wording and style, preserve that voice; just make it shorter and tighter.
  • Write in the user's own first-person voice — a short, honest personal note, not marketing copy.

Local macOS apps

  • Sign apps that need Accessibility, Screen Recording, microphone, camera or similar grants with a stable local identity. Ad-hoc signatures change identity on every build, leaving enabled privacy toggles that the rebuilt app cannot use.
  • Make the build fail when its expected signing identity is missing. Do not silently fall back to ad-hoc signing.

Markdown

  • Use Peter Hartree's Roughdraft fork as the default Markdown review tool.
  • Open files with roughdraft open "/absolute/path/to/file.md".
  • After the user reviews or closes a document, reread the file for CriticMarkup feedback.

Read README.md for this project's purpose, setup and current state.

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 First seen · 46 lines · 464 tokens per session scan A ea9095a29a30

Subscribe to this mod's changes

gdoc-mcp AGENTS.md is an instructions file published in the GitHub repository alejoacelas/gdoc-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 464 tokens to every session, about $0.0019 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 2026-09-09.

Related

gdoc-mcp AGENTS.md compared with instructions from other repositories

gdoc-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gdoc-mcp AGENTS.mdalejoacelas/gdoc-mcpInstructions file01mo agoMITA464Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode