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.
npx agentmods add rules/jaichangpark/workshop-harness/cursorrulesgit clone --depth 1 https://github.com/JAICHANGPARK/workshop-harnessWhat 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 | $0.00344 | $0.00344 |
| Opus 5 | $0.00172 | $0.00172 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
cursorrules 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 yesterday.
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.
What it actually says
.cursorrules - Workshop Harness Cursor Rules
Follows AGENTS.md open specification (https://agents.md/)
You are an expert AI Coding Agent assisting technical workshop facilitators.
CRITICAL RULES:
- MANDATORY AUTONOMOUS WEB SEARCH: Never rely on internal training weights for technical code generation. Autonomously execute live web searches to verify latest SDK methods (e.g. google-genai, Pydantic V2) and current model tags (e.g. gemini-3.7-flash, claude-sonnet-5, gpt-5.6-sol, gemma4).
- DEVELOPER-IDIOMATIC LOCALIZATION: When translating or authoring slides and docs into Korean, Japanese, or Chinese, do NOT use literal machine translations. Always use industry-standard developer jargon (e.g., KR: "프롬프트 엔지니어링", "핸즈온 랩", "스캐폴딩", "런북").
- NO EM DASH: NEVER generate em dash characters (
—or\u2014). Always use standard hyphens (-), colons (:), or parentheses. - NO EMOJIS IN DOCUMENTATION: Do NOT include emojis in generated documentation, slides, or code comments by default, unless the user explicitly requests emojis.
- NATURAL LANGUAGE AUTONOMY: Users communicate via natural language chat prompts. Do NOT instruct users to manually run Python CLI commands. Autonomously inspect
skills/*/SKILL.mdand execute tools on their behalf. - Keep generated code and markdown clean, production-ready, and verified for broken links.
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.
- yesterday First seen · 13 lines · 344 tokens per session scan A be12d73da617
cursorrules is a cursor rule published in the GitHub repository JAICHANGPARK/workshop-harness (5 stars, last pushed 3d ago), licensed MIT. It adds 344 tokens to every session, about $0.0017 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
internationalization
Cursor rule "internationalization" from dtyq/magic, covering internationalization (i18n) rules, 国际化基本规范, 1. 文件结构, 2. 命名空间规范 and 3. 组件中使用国际化.
07-datagen
IF 生成物品/方块模型 JSON → 手动编写 JSON 在 src/main/resources/assets/{modid}/models/.
test-plan
Plan Katalon True Platform/TestOps testing for a release, sprint, or feature. Use when you need to translate quality goals into scope, prioritize testing by requirement coverage and risk, decide what to test first, or build the executable plan structure (folders, suites, and sprint/release association) that stands in…
wings
Authoring apps with the WINGS framework (Go compiled to WASM web components).
project-status
PriceGrab shipped state and product backlog (read first).
architecture
Architectural and cross-package changes — dependency direction, editor/runtime boundaries, scene schema, persistence, renderer packages. Use when changing package boundaries, serialized formats, or multiple layers. Do not apply to localized UI, styling, or test-only edits.