mac-yolo-safeguards / hermes-mobile
AGENTS.md3 starsChanged 3 days agoMITView on GitHub
Canonical repo rules: ../AGENTS.md. This file adds mobile-only obligations so agents do not wait for the user to ask.
- Reads credentials
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 32,671 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
- 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-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 AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 51
North star: Every launch is a stranger who knows nothing.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md 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
AGENTS.md — Hermes Mobile
Canonical repo rules: ../AGENTS.md. This file adds mobile-only obligations so agents do not wait for the user to ask.
Standing orders (no reminders)
- Before any edit — run
../../bin/agent-loop --health(validates hooks, MCP, skills, E2E, plan claims). Full cycle:../../bin/agent-loop(Recollect→Plan→Observe→Act→Evaluate→Learn). - Session start — parent repo runs
node tools/agent-session-start.js(pairing, LaunchAgent health, continuous E2E status). Do not skip when touching this tree. - After any edit under
src/,app.json, or.maestro/— in the same turn before claiming fixed/shipped:npm test -- --no-coverage --watchman=false- Kick autonomous E2E:
launchctl kickstart -k "gui/$(id -u)/com.igor.hermes-mobile-continuous-e2e"ornpm run e2e:continuous:once
- Never ask the user to run Maestro, reload Metro, plug in a phone, or tap Send — use
adb,hermes-mobile-pair.js, and scripts. - Read
docs/proofs/continuous/latest.jsonbefore saying chat/E2E is healthy. Ife2e≠pass, say so with the JSON — do not claim device UX is verified. - Phone connected (
adb devices) → E2E prefers Android automatically viascripts/run-e2e.sh. - Phone install only via release path —
npm run android:phoneorscripts/install-phone-release.sh; neverexpo run:androidon device (npm run androidblocks when adb sees a phone). - RN performance work — read
.cursor/skills/react-native-best-practices/SKILL.mdfirst (Callstack 2026 optimization guide skills). Install/refresh:bash ../scripts/install-callstack-agent-skills.sh. Measure before optimizing. - Real users product — Hermes Mobile ships to real users, not Igor-only dogfood. No feature is "done" if it requires
adb, dev backdoor, or pre-paired Igor Mac. - Brand-new user testing (permanent) — always treat every test as if it is a brand new user: fresh install, no saved profiles, no
developerLeashUnlock, cellular or Wi‑Fi only, release APK. Maestro and manual proofs must reflect that mindset. - Multi-Mac API keys — Mac mini and MacBook Pro can have different
API_SERVER_KEYvalues. Pair mini vianode tools/hermes-mobile-pair.js --mini-tailscale(SSH-fetches mini key); never paste the laptop.envkey when targeting another machine. - Device/Maestro chat input (permanent) — When testing via Maestro,
adb input text,agent-device, or any device/E2E automation that types into the chat composer, use onlymake money today. Never type gibberish probe strings (typeableProbeB,e2e-chat-send-persist,smoke test message, etc.). Session titles/IDs in URLs are exempt. Enforced bypreventRecurrenceContract.test.ts. - Versioning / OTA / store — JS fixes ship via EAS Update (
productionchannel, CImobile-ota.yml). New store binaries only for native changes or marketingexpo.versionbumps. Canonical rules: docs/VERSIONING-AND-RELEASES.md. Do not claim “every fix needs the store” or invent semver automation that does not exist. - No production OTA without fresh-user gate (permanent, crisis 2026-07-15) — Never run
eas update --channel production/npm run ota:publishunlessdocs/proofs/continuous/latest.jsonhase2e=passornpm run e2e:fresh-user(.maestro/stranger-cold-start.yaml) wrote a pass proof. Gate:npm run ota:gate→scripts/require-fresh-user-ota-gate.sh. CI must not auto-publish production on everymainmerge.e2e=skippedis not pass. - agent-device (Callstack) — For connection-crisis / Tailscale / fresh-user UI proofs, use
agent-device(orbash scripts/agent-device-connection-proof.sh). Install/refresh:bash ../scripts/install-agent-device.sh. Matrix vs Maestro vs adb: docs/AGENT-DEVICE.md. Maestrolatest.jsonremains the ship gate; agent-device alone is note2e=pass. Do not claim Connected when UI shows Reconnecting. - No desktop hijack — Never drive Igor's interactive Google Chrome, steal macOS focus, or use Computer Use unless he explicitly asked in that message. Parent rule: ../AGENTS.md § No desktop hijack. Prefer
gh, Play/ASC APIs, Stripe CLI,adb, SSH. Chrome CDP LaunchAgents stay gated off (HERMES_ALLOW_INTERACTIVE_CHROMEdefault 0).
Autonomous infrastructure (already installed on Igor's Mac)
| Piece | Interval | Check |
LaunchAgent com.igor.hermes-mobile-continuous-e2e | 15 min | npm run e2e:continuous:status |
GitHub mobile-continuous.yml | 6 h | unit + coverage on push schedule |
Install/repair: bash ../scripts/install-agent-launchagents.sh (agent runs this if missing — not the user).
Verification ladder
| Layer | Command |
| Unit | npm test / npm run test:ci |
| Contract | npm run test:release-safety |
| Connection UI proof | bash scripts/agent-device-connection-proof.sh (exploratory; see AGENT-DEVICE.md) |
| E2E (local) | npm run e2e:continuous:once |
| E2E (fresh-user / OTA gate) | npm run e2e:fresh-user then npm run ota:gate |
| E2E (device release) | npm run e2e:device |
| Accelerated Maestro | npm run e2e:accelerated (agent-device test --maestro) |
Details: docs/TESTING.md.
Fresh-user onboarding contract (permanent)
North star: Every launch is a stranger who knows nothing. One primary CTA per connection state. Silent auto-heal ~30s before numbered human steps.
| State | User sees | Must NOT see |
| First launch, no saved Mac | ConnectMacGate + numbered steps + Find computers | "Pair relay", "gateway", "LAN", competing banners |
| Disconnected, saved Mac | Silent heal in CodexCommandCenter; after ~30s ChatConnectionPanel + steps | "Connected" + "Can't reach" at once |
| Choose Mac modal | Tailscale Add [name] at top when tailnet probe succeeds | Mac mini buried only in Settings |
| Cellular, no Tailscale | Step 4 + Use Tailscale from cellular title | Home Wi‑Fi IP instructions without context |
Infer onboarding complete from valid saved gatewayProfiles (no separate flag required).
Unit tests (required on onboarding copy changes):
src/__tests__/freshUserOnboarding.test.ts— step copy, heal timing, jargon-freesrc/__tests__/FreshUserOnboardingCard.test.tsx— numbered steps rendersrc/__tests__/ChatConnectionPanel.test.tsx— fresh-user card, single CTA, Tailscale chip
Maestro: connect-mac-gate must show connect-mac-onboarding-card on cold start without demo deep link (future flow); demo bootstrap uses hermes://setup?demo=1 and hides the gate.
Copy rules: Say Your Mac, Home Wi‑Fi, Find computers — never "gateway", "LAN", or "Pair relay" in first-run / disconnected primary UI.
Greptile AI PR review
Version-controlled rules: ../.greptile/ + .greptile/. Agent guide: docs/GREPTILE-CODE-REVIEW.md.
On PRs that touch connect, onboarding, pairing, Tailscale, auth probes, OTA, or multi-Mac keys: read Greptile findings before claiming fixed/shipped. Force review with @greptileai review once the GitHub App is installed. Do not treat green CI alone as connect/onboarding proof when Greptile flags a fresh-user or wrong-key regression class.
Prevent recurrence (July 2026)
Playbook: docs/PREVENT-RECURRENCE-JULY-2026.md. Session gates: vault pull + plan.md §2 before parallel work; bash scripts/agent-adb-refresh.sh before phone/pair; bash scripts/agent-pre-asc-edit.sh before ASC review notes; read docs/proofs/continuous/latest.json before device/chat ship claims (e2e=skipped is not pass). Cursor: single-pass — no duplicate subagents on the same file domain or PR.
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.

