mac-yolo-safeguards / rules
Cursor rule3 starsChanged 3 days agoMITView on GitHub
Hermes Mobile is a real-user product — never dogfood-only assumptions in tests or UX
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,243 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository153 other files it gives its agents.
- AGENTS.mdAGENTS.md
- hermes-mobile/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/agent-automations.mdcCursor rule
- .cursor/rules/agent-device.mdcCursor rule
- .cursor/rules/agent-harness-router.mdcCursor rule
- .cursor/rules/agent-skills-overview.mdcCursor rule
- .cursor/rules/always-agent-mode.mdcCursor rule
- .cursor/rules/callstack-agent-skills-overview.mdcCursor rule
- .cursor/rules/callstack-react-native-best-practices.mdcCursor rule
- .cursor/rules/codeql-agent-hygiene.mdcCursor rule
- .cursor/rules/decision-stack.mdcCursor rule
- .cursor/rules/expo-credit-budget.mdcCursor rule
- .cursor/rules/fleet-repo-intelligence.mdcCursor rule
- .cursor/rules/hermes-mobile-prevention-july-2026.mdcCursor rule
- .cursor/rules/hermes-mobile-verification.mdcCursor rule
- .cursor/rules/no-desktop-hijack.mdcCursor rule
- .cursor/rules/no-manual-handoffs.mdcCursor rule
- .cursor/rules/obsidian-teammate-collaboration.mdcCursor rule
- .cursor/rules/prefer-headless-background-ops.mdcCursor rule
- .cursor/rules/react-native-best-practices.mdcCursor rule
- public/llms.txtllms.txt
- advertise-thumbgate-github-marketplaceSkill
- agent-harness-routerSkill
- agentic-pattern-selectorSkill
- agents-judgment-calls-gateSkill
- ai-native-sdlcSkill
- android-dev-summit-26-gateSkill
- anti-babysitting-mandateSkill
- anti-babysittingSkill
- background-agent-hold-gateSkill
- browseros-agent-harnessSkill
- webmcp-agent-readinessSkill
- ci-first-failSkill
- ci-pr-monitorSkill
- cloudflare-developer-stackSkill
- cloudflare-kitesurf-browserSkill
- cloudflare-monetization-gatewaySkill
- confidence-offer-gateSkill
- content-laneSkill
- context-six-blockSkill
- context-vaultSkill
- context-weight-gateSkill
- dual-model-agentic-graphragSkill
- egm-fresh-reviewSkill
- elevenlabs-voice-agentsSkill
- emeans-quant-and-instinctSkill
- explainx-trending-honestSkill
- explainx-trending-ragSkill
- future-agi-self-healing-engineSkill
- garryslist-opportunity-trackerSkill
- gemini-decisions-hold-gateSkill
- git-at-scaleSkill
- gitbutler-fleet-automationsSkill
- gitbutler-google-ssoSkill
- gitbutler-mcp-isolatedSkill
- gitbutler-session-absorbSkill
- git-hooks-no-huskySkill
- github-marketplace-action-publishSkill
- The first 60 shown.
The file
We split this hermes-mobile-real-users.mdc into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Before claiming fixed, shipped, or "works on device", assume the tester has:
- Distinctive: line 18
Never paired before; no saved gateway profiles.
- Distinctive: line 21
No knowledge of Mac hostname, tunnel URLs, or relay codes
- Very specific: line 24
Do not pass tests that only work because Igor's Mac is plugged in, adb reverse is set, or developerLeashUnlock is on.
- Very specific: line 42
Tests: Run npm run test:ci; onboarding copy guarded by freshUserOnboarding.test.ts, FreshUserOnboardingCard.test.tsx, …
≈ “Common” is an estimate: at least 1 in 5 of the 6,809 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.
Files
--- description: Hermes Mobile is a real-user product — never dogfood-only assumptions in tests or UX globs: - hermes-mobile/** alwaysApply: false --- # Hermes Mobile — real users product **User directive (permanent):** Hermes Mobile is a product for **real users**, not Igor-only USB dogfood. ## Brand-new user mindset (every test) **Always treat every test as if it is a brand new user.** Before claiming fixed, shipped, or "works on device", assume the tester has: - Never paired before; no saved gateway profiles; no dev backdoor unlocked - No `adb` cable; may be on **cellular** or home Wi‑Fi only - Installed from **release APK / Play** — not Metro, not debug dev-client - No knowledge of Mac hostname, tunnel URLs, or relay codes - First launch: empty recents, honest disconnected copy, onboarding must work Do **not** pass tests that only work because Igor's Mac is plugged in, `adb reverse` is set, or `developerLeashUnlock` is on. ## Product bar - Onboarding: QR/deep link / Find computers — not "paste 127.0.0.1" without context - Leash Pro / ThumbGate API for subscribers — dev backdoor is Igor-only, not the user path - Cellular + multi-Mac: tunnel wizard copy must be actionable - Maestro E2E on release build where possible; unit tests must not assume Igor fixtures as "default user" See `hermes-mobile/docs/REAL-USER-READINESS.md` when present. ## Fresh-user test contract 1. **Cold start (no profiles):** `ConnectMacGate` shows `fresh-user-onboarding-card` with steps 1–4 and primary CTA **Find computers** (`connect-search-wifi`). 2. **Silent heal:** Returning users with a saved Mac get ~30s auto-heal (`CONNECTION_HEAL_EXHAUSTED_AFTER=6` × 5s) before `ChatConnectionPanel` + numbered steps; status pills hidden during heal. 3. **One CTA:** Exactly one primary button in connection UI (Find computers / Fix USB connection / Add [Mac] via Tailscale chip — not three competing banners). 4. **Tailscale on cellular:** `TailscaleDiscoveryBanner` with **Add Igors-Mac-mini** (or discovered hostname) appears in **Choose your Mac** modal and connection panel — not Settings-only. 5. **Jargon ban in primary onboarding:** No "gateway", "LAN", "Pair relay" in `ConnectMacGate`, `FreshUserOnboardingCard`, or `ChatConnectionPanel` hero copy. 6. **Tests:** Run `npm run test:ci`; onboarding copy guarded by `freshUserOnboarding.test.ts`, `FreshUserOnboardingCard.test.tsx`, `ChatConnectionPanel.test.tsx`.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

