workspace-policy

workspace-policy is a cursor rule for Cursor from vanessamarely/ai-playbook-reposito. It costs 1,211 tokens per session, scanned A, original, MIT.

A set of workspace rules for keeping coding projects separate and telling different AI coding tools where to find their instruction files.

In plain words
What is it for?
Use it to organize instruction files for GitHub Copilot, Claude Code, Cursor, and OpenAI Codex CLI, including rules for nested projects.
Why use it?
It removes uncertainty about which instructions each tool reads and where project-specific rules belong.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Good fit Use it to organize instruction files for GitHub Copilot, Claude Code, Cursor, and OpenAI Codex CLI, including rules for nested projects.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/vanessamarely/ai-playbook-reposito/workspace-policy
Install

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.

Clone the repo
git clone --depth 1 https://github.com/vanessamarely/ai-playbook-reposito

Made for: Cursor.

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-policy

README.md
[![agentmods](https://agentmods.dev/badge/rules/vanessamarely/ai-playbook-reposito/workspace-policy/github.svg)](https://agentmods.dev/rules/vanessamarely/ai-playbook-reposito/workspace-policy)
Your own site
<a href="https://agentmods.dev/rules/vanessamarely/ai-playbook-reposito/workspace-policy"><img src="https://agentmods.dev/badge/rules/vanessamarely/ai-playbook-reposito/workspace-policy/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-policy

Your own site · 80×15
<a href="https://agentmods.dev/rules/vanessamarely/ai-playbook-reposito/workspace-policy"><img src="https://agentmods.dev/badge/rules/vanessamarely/ai-playbook-reposito/workspace-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,211 This file is loaded in full into every session.
When invoked 1,211 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 $0.01211 $0.01211
Opus 5 $0.00606 $0.00606
Sonnet 5 $0.00242 $0.00242
Haiku 4.5 $0.00121 $0.00121

Measured 10d ago against content hash 5d4ed8516b6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

workspace-policy 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 10d 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.

ai-playbook/.cursor/rules/workspace-policy.mdc · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Policy

Supported AI Tools

This playbook supports four AI coding assistants. Each has its own discovery mechanism — there is no shared folder all of them read.

AI Tool Always-loaded instructions Location
GitHub Copilot copilot-instructions.md <repo-root>/.github/copilot-instructions.md
Claude Code CLAUDE.md <repo-root>/CLAUDE.md
Cursor .mdc rules (alwaysApply: true) <repo-root>/.cursor/rules/*.mdc
OpenAI Codex CLI AGENTS.md <repo-root>/AGENTS.md (nearest wins for nested overrides)

Run /ai-tool-setup to generate or refresh instruction files for all four tools.

Rules, Commands, and Skills (Cursor)

As of Cursor 2.4 (January 2026), Cursor natively reads Agent Skills — the same open SKILL.md format used by Claude Code and Codex CLI — directly from .cursor/skills/<name>/SKILL.md (project) or ~/.cursor/skills/ (personal); it also reads the shared .agents/skills/ location and, for legacy compatibility, .claude/skills/ and .codex/skills/. All three Cursor mechanisms coexist and serve different purposes:

Mechanism Location Purpose
Rules .cursor/rules/*.mdc Short, always-on or glob-scoped guidance auto-attached by file type (like this document)
Commands .cursor/commands/*.md Simple one-off actions invoked explicitly with /name
Skills .cursor/skills/<name>/SKILL.md Longer, multi-step procedures — explicitly invoked with /name or model-selected from name/description, optionally scoped to file types via a paths frontmatter field, and able to bundle scripts/, references/, and assets/ subfolders

This playbook's 13 procedures (the 6 skills and 7 former-agents under .claude/skills/ and .claude/agents/) are ported to Cursor as native skills under .cursor/skills/<name>/SKILL.md. The routing table below points at those files. The existing .cursor/rules/*.mdc file-type rules and .cursor/commands/*.md commands remain valid and continue to work — this is additive, not a replacement.

Read the full file on GitHub · 87 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. 10d ago First seen · 87 lines · 1,211 tokens per session scan A 5d4ed8516b6b

Subscribe to this mod's changes

workspace-policy is a cursor rule published in the GitHub repository vanessamarely/ai-playbook-reposito (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,211 tokens to every session, about $0.0061 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 2026-08-31.