mac-yolo-safeguards / rules
Cursor rule3 starsChanged 3 days agoMITView on GitHub
User directive (emphatic): never abuse Expo/EAS credits and never cause an overage bill again. Root incident: 121 mobile-ota.yml runs in 48h (2026-07-23) drove an ~$78 Expo charge that the card declined. Batch every merged JS fix into one OTA. Never publish per-PR. Related: AGENTS.md, hermes-mobile/docs/OTA_UPDATES.md, hermes-mobile/docs/VERSIONING-AND-RELEASES.md.
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/fleet-repo-intelligence.mdcCursor rule
- .cursor/rules/hermes-mobile-prevention-july-2026.mdcCursor rule
- .cursor/rules/hermes-mobile-real-users.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 expo-credit-budget.mdc into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
User directive (emphatic): never abuse Expo/EAS credits and never cause an overage bill again.
- Very specific: line 23
Check the budget guard (tools/ota-publish-budget.js / hermes-mobile/scripts/ota-spend-guard.js) — if it exits non-zero, stop.
- Very specific: line 26
Prefer zero-cost verification: npm test, local release APK via npm run android:phone, adb.
≈ “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
--- alwaysApply: true --- # Never abuse Expo credits — no overages (permanent, 2026-07-24) **User directive (emphatic):** never abuse Expo/EAS credits and never cause an overage bill again. Root incident: 121 `mobile-ota.yml` runs in 48h (2026-07-23) drove an ~$78 Expo charge that the card declined. ## Hard budget | Limit | Value | |-------|-------| | Production OTA publishes | **≤ 1 per 24h** | | `mobile-ota.yml` runs (incl. failures) | **≤ 3 per rolling 48h** | | EAS **cloud builds** | only for native changes or a deliberate store binary — never to test JS | | Retry after a failed publish | fix the cause first; a retry consumes budget | Batch every merged JS fix into **one** OTA. Never publish per-PR. ## Before any EAS spend 1. Check the budget guard (`tools/ota-publish-budget.js` / `hermes-mobile/scripts/ota-spend-guard.js`) — if it exits non-zero, **stop**; do not bypass. 2. `HERMES_OTA_BILLING_THAW=1` may only be set when the spend guard is wired **and** billing is not mid-decline. Never set it to unblock a single impatient publish. 3. `npm run ota:gate` — needs continuous `e2e=pass` or a fresh-user proof. `e2e=skipped` is not pass. 4. Prefer zero-cost verification: `npm test`, local release APK via `npm run android:phone`, `adb`. Never spend EAS credits to observe a JS change. ## Banned - Looping / re-dispatching `mobile-ota.yml` to "see if it works" - Cloud builds as a substitute for local device testing - Bypassing the spend guard or thaw gate with `FORCE_*` without Igor's explicit same-message ask - Claiming OTA shipped without an `eas update:list` group id Related: [AGENTS.md](../../AGENTS.md), [hermes-mobile/docs/OTA_UPDATES.md](../../hermes-mobile/docs/OTA_UPDATES.md), [hermes-mobile/docs/VERSIONING-AND-RELEASES.md](../../hermes-mobile/docs/VERSIONING-AND-RELEASES.md).
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.

