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 instructions/hy4ri/hermes-mobile/agents-mdgit clone --depth 1 https://github.com/Hy4ri/hermes-mobileWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/hy4ri/hermes-mobile/agents-md)<a href="https://agentmods.dev/instructions/hy4ri/hermes-mobile/agents-md"><img src="https://agentmods.dev/badge/instructions/hy4ri/hermes-mobile/agents-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.03753 | $0.03753 |
| Opus 5 | $0.01877 | $0.01877 |
| Sonnet 5 | $0.00751 | $0.00751 |
| Haiku 4.5 | $0.00375 | $0.00375 |
Grade A, and why
hermes-mobile AGENTS.md scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sSLO https://github.com/pinterest/ktlint/releases/download/1.8.0/ktlint How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working on this repository.
This complements README.md (for humans) and DESIGN.md
(architecture & design rationale) with agent-focused context. Before making any
non-trivial architectural change — new screens, navigation changes, theme/state
patterns, module boundaries — read DESIGN.md first and keep changes consistent
with the decisions recorded there. If a change would contradict DESIGN.md,
flag it explicitly rather than silently diverging.
Project Overview
Hermes Mobile is a Jetpack Compose Android app — a mobile control panel for Hermes Agent. It talks to the Hermes dashboard's REST API and WebSocket TUI Gateway (JSON-RPC 2.0) over a trusted LAN.
- Package:
com.m57.hermescontrol - Min SDK 26 / Target SDK 37 / Compile SDK 37
- Kotlin 2.4.10, KSP 2.3.10 (standalone versioning, NOT
kotlinVersion-kspVersion) - Jetpack Compose, Room 2.7.x, Navigation3, OkHttp WebSocket, Retrofit, Kotlinx Serialization
- Auth:
EncryptedSharedPreferences(AES256-GCM), Bearer token (REST) +?token=(WS)
Build & Test Commands
✅ Local Android SDK — if available
If you have a local Android SDK (ANDROID_HOME set), these work:
./gradlew assembleDebug # full APK build
./gradlew testDebugUnitTest # unit tests (MockK)
./gradlew ktlintCheck # style check
ktlint standalone (no SDK needed):
# Download the matching binary
curl -sSLO https://github.com/pinterest/ktlint/releases/download/1.8.0/ktlint
chmod +x ktlint
./ktlint <file> # check one file
./ktlint --format <file> # auto-fix
No SDK? CI handles everything — push small and watch the checks below.
CI pipeline (.github/workflows/android.yml)
| Job | Purpose |
|---|---|
ktlint |
ktlint 1.8.0 style check + checkColorLiterals (hardcoded Color guard, issue #622) |
android-lint |
Android Lint |
unit-tests |
JUnit |
build |
assembleDebug (gated by the 3 above) |
release-compile |
compileReleaseKotlin — catches release-variant compilation issues (e.g. debugImplementation-scoped deps referenced in main source) |
instrumented-tests |
Compose UI tests on Android emulator (API 34 ATD) |
ci-summary |
Aggregator (if: always()) — branch protection gates on THIS check |
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.
- today Changed b51247e5509f
- 4d ago First seen · 324 lines · 3,753 tokens per session scan A 0238f1907846
hermes-mobile AGENTS.md is an instructions file published in the GitHub repository Hy4ri/hermes-mobile (105 stars, last pushed today), licensed Apache-2.0. It adds 3,753 tokens to every session, about $0.0188 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
sceneview copilot-instructions.md
Copilot instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.
debroid AGENTS.md
Instructions for PatilShreyas/debroid, covering ai agent contributor guide 🤖, 🎯 intention & motivation, 🏗️ architecture & layers, 1. the core layer (jdi & adb orchestration) and 2. the cli layer (daemon & client).
PdfKmp CLAUDE.md
Instructions for ConaMobileDev/PdfKmp, covering claude.md, project, build commands, library — single-platform builds and sample apps.
DSH-Mobile AGENTS.md
AGENTS.md instructions for SimonMedy/DSH-Mobile, covering agents.md — dsh mobile engineering contract, product boundary, security invariants, dependency policy and architecture.
capacitor-mobile-claw CLAUDE.md
Claude Code instructions for sernnee/capacitor-mobile-claw, covering claude.md — ai-assisted development context, project overview, repository structure, build & test commands and key architecture.
mobile-ai-agents CLAUDE.md
Claude Code instructions for salmanashraf/mobile-ai-agents, covering claude.md — mobile ai agents, what this repo is, quick start, install everything and install by platform.