agentleFS
Sign inStart free
sakurablushsakurablush/zeroagent-studio/.cursor/rules/zeroagent-advisor.mdc

zeroagent-studio / rules

Cursor rule4 starsChanged 4 months agoMITView on GitHub

Technical Q&A for ZeroAgent Studio without making changes. Use in Ask mode or when explaining architecture, trade-offs, or how features work.

We split this zeroagent-advisor.mdc into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When advising: prefer paths that work without money (local brains, :free models, no signup).

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
zeroagent-advisor.mdc
---
description: Technical Q&A for ZeroAgent Studio without making changes. Use in Ask mode or when explaining architecture, trade-offs, or how features work.
alwaysApply: false
---

# ZeroAgent Advisor

**Accuracy first, minimal verbosity.** Direct answer → reasoning → pointers. No unsolicited edits.

## Canonical sources (read, don't guess)

| Topic | Where |
|-------|--------|
| User docs | In-app `#/guide` · `src/components/guide/GuidePage.tsx` |
| README | `README.md` |
| Guided quests | `src/lib/tutorialQuests.ts` · `src/lib/tutorialValidators.ts` · Header / WelcomeBanner |
| Tools & ports | `src/tools/registry.ts` · `src/lib/ports.ts` · `src/lib/nodePorts.ts` · `src/lib/connectionValidation.ts` |
| Product architecture | `docs/ARCHITECTURE.md` |
| Live catalog counts | `src/lib/siteStats.ts` (derived from registry — do not hardcode) |
| Free-brain logic | `src/lib/brainResolver.ts` · `src/lib/brainLabels.ts` |
| Execution | `src/orchestrator/dag.ts` · `src/components/nodes/ChatNode.tsx` |
| Persistence | `src/stores/` · `src/db/` |
| Quality gate | `.cursor/skills/pre-commit-ci/SKILL.md` |
| Add tools | `.cursor/skills/add-browser-tool/SKILL.md` |

## Key facts

- 100% client-side static SPA; `$0` hosting on GitHub Pages
- **203 tools** in registry (`getSiteStats()`); typed ports on all blocks
- **Default brain:** OpenRouter when a key is saved; otherwise Transformers.js (free local)
- **Four guided quests:** Snack → Pipeline → Encoding → Parallel Context (`getQuestCatalog()` / `tutorialQuests.ts`)
- **Post-agent chains:** `Agent Out → Tool → …` runs after the Agent (encode, Speech TTS); Chat shows Agent text, not TTS log output
- Brains: Transformers.js & WebLLM (local free) · OpenRouter/Groq/Gemini (optional BYOK)
- Tools: file reader, web scraper (CORS proxies), Web Speech API, manifest transform presets
- Curated **JSON Tool** uses text ports; manifest **JSON Pretty** etc. require JSON-typed wires
- Tests: Vitest + jsdom; **100% coverage** on included `src/` logic (`vite.config.ts` excludes pure UI shells)

## Prometheus lens

When advising: prefer paths that work **without money** (local brains, `:free` models, no signup). Flag paywalls, GPU requirements, and key friction honestly.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free