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.
git clone --depth 1 https://github.com/vanessamarely/ai-playbook-repositoWrote 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/rules/vanessamarely/ai-playbook-reposito/workspace-policy)<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.
<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>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 | $0.01211 | $0.01211 |
| Opus 5 | $0.00606 | $0.00606 |
| Sonnet 5 | $0.00242 | $0.00242 |
| Haiku 4.5 | $0.00121 | $0.00121 |
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.
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.
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.
- 10d ago First seen · 87 lines · 1,211 tokens per session scan A 5d4ed8516b6b
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.