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/commands/vanessamarely/ai-playbook-reposito/skill-creator)<a href="https://agentmods.dev/commands/vanessamarely/ai-playbook-reposito/skill-creator"><img src="https://agentmods.dev/badge/commands/vanessamarely/ai-playbook-reposito/skill-creator/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/commands/vanessamarely/ai-playbook-reposito/skill-creator"><img src="https://agentmods.dev/badge/commands/vanessamarely/ai-playbook-reposito/skill-creator.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 | $0.00000 | $0.00724 |
| Opus 5 | $0.00000 | $0.00362 |
| Sonnet 5 | $0.00000 | $0.00145 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
skill-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
Scaffold a new Cursor rule or command that follows this playbook's conventions — proper structure, and agent-oriented procedural instructions. Use when the user wants to add a new automated procedure, convert prose documentation into a rule/command, or validate an existing one. Not for human-facing README files, changelogs, or general project documentation.
Inputs
- Name (lowercase, numbers, hyphens only).
- Purpose and scope.
- Target procedures and decision points.
- Whether it should be a rule (passive, auto-loaded context) or a command (explicit
/nameinvocation).
Outputs
- A new
.cursor/rules/<name>.mdcor.cursor/commands/<name>.mdfile.
Procedure
- Validate the name — lowercase letters, numbers, and hyphens only (
^[a-z0-9-]+$); must match the filename; must be unique within.cursor/rules/and.cursor/commands/. Reject and give an example if invalid. - Decide rule vs. command:
- Rule (
.cursor/rules/<name>.mdc) — passive context that should apply automatically. ChoosealwaysApply: truefor policies that always matter,globs: "<pattern>"for file-type-triggered guidance, or a strongdescriptionwith neither for "Agent Requested" (loaded when relevant to the task at hand). - Command (
.cursor/commands/<name>.md) — an explicit, one-off invokable action. No frontmatter needed.
- Rule (
- Write the frontmatter (rules only):
description(action-oriented, third person, under ~200 characters, no first/second-person pronouns), plusglobsoralwaysApplyas decided in step 2. - Write the purpose — one paragraph: what it accomplishes, when it should apply/be invoked, and explicit scope boundaries (what it does NOT do).
- Write inputs — parameter name, type, description, default if applicable.
- Write outputs — files created/modified, commands to run, data returned.
- Write the procedure — numbered, deterministic steps in third-person imperative ("Validate", "Generate", "Verify"), with explicit if/else branches where behavior differs.
- Write error handling — failure mode, how it's detected, the remediation step.
- Keep it single-file — Cursor has no native folder of bundled scripts/references/assets like some other tools. Inline the essential guidance directly in the
.mdc/.mdfile; condense verbose examples rather than splitting into a supporting-files tree. - Keep it focused — if the file is growing unwieldy, split into a narrower rule/command rather than adding a references folder that Cursor won't auto-load.
- Validate metadata — name format, description length, no first/second-person pronouns ("I", "you", "we").
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 · 38 lines · 0 tokens per session scan A 41971dbd3558
skill-creator is a command published in the GitHub repository vanessamarely/ai-playbook-reposito (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 724 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.