faq_usage

A reference guide for the repository’s design decisions and the reasons behind them. It covers the project charter, skills versus plugins, decision records, and validation.

In plain words
What is it for?
Use it when changing the repository’s architecture, deciding what belongs in it, or documenting why a design choice was made.
Why use it?
It helps contributors understand the reasoning behind the repository structure before changing architecture or inclusion rules. It also points to fuller decision records when more detail is needed.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/arenukvern/skill_steward/faq_usage
Clone the repo
git clone --depth 1 https://github.com/Arenukvern/skill_steward

Made for: Cursor.

Per session 607 This file is loaded in full into every session.
When invoked 607 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00607 $0.00607
Opus 5 $0.00303 $0.00303
Sonnet 5 $0.00121 $0.00121
Haiku 4.5 $0.00061 $0.00061

Measured 3d ago against content hash 2610e5b7ebc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

faq_usage 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 3d 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.

.cursor/rules/faq_usage.mdc · 39 lines

What it actually says

FAQ Documentation Usage Guide — Skill Steward

Q: What is DESIGN_FAQ.mdx for?
A: Explains why Guild repo decisions were made (meta-layer charter, skills vs plugins, ADRs, validation). Use when changing architecture, inclusion criteria, or documenting rationale. Path: docs/DESIGN_FAQ.mdx.

Q: What is DX_FAQ.mdx for?
A: Explains how to contribute and install (npx skills, pnpm run validate, add skill workflow). Memory Palace format. Path: docs/DX_FAQ.mdx.

Q: What is the difference from docs/decisions/ ADRs?
A: ADRs are formal decision records for significant changes. DESIGN_FAQ is a compressed index of standing why answers; link to ADRs for full deliberation.

Q: What about package-level FAQs?
A: This repo has root FAQs only. When adding sub-packages with their own boundaries, add DESIGN_FAQ.mdx + DX_FAQ.mdx there and router rows; use repository-governance-lifecycle for durable doc-lattice changes.

Q: What format should DX_FAQ.mdx use?
A: Memory Palace — emoji locations with terse code blocks (install, validate, add skill). Optimized for agent recall.

Q: Where is the charter?
A: docs/NORTH_STAR.mdx — not DESIGN_FAQ. Use repository-governance-lifecycle when changing scope or the AGENTS map.

Q: When should I reference DESIGN_FAQ.mdx?
A: Scope questions (“does this skill belong in Guild?”), plugins vs skills, documentation strategy, rejection of domain skills.

Q: When should I reference DX_FAQ.mdx?
A: Installing Guild, adding a skill, running validate, updating registry files, choosing which doc skill to use.

Q: Can I use both FAQs together?
A: Yes. Example: DESIGN explains why plugins need a separate hook install; DX shows the npx skills commands. No duplicated paragraphs.

Q: Which FAQ should I update after a change?
A: Architectural or charter whydocs/DESIGN_FAQ.mdx (+ new ADR if significant). Contributor workflow howdocs/DX_FAQ.mdx. Skill behavior → skills/{name}/SKILL.md only.

Q: Should I update FAQs when adding a skill?
A: Update docs/DX_FAQ.mdx only if the maintainer workflow changes. Update docs/DESIGN_FAQ.mdx only if the change affects repo-level why. Always update README.md, skills.sh.json, and run pnpm run validate.

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. 3d ago First seen · 39 lines · 607 tokens per session scan A 2610e5b7ebc8

Subscribe to this mod's changes

faq_usage is a cursor rule published in the GitHub repository Arenukvern/skill_steward (11 stars, last pushed 18d ago), licensed MIT. It adds 607 tokens to every session, about $0.0030 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 2026-08-30.