agentmods.dev

Autofish AGENTS.md

Autofish AGENTS.md is an instructions file for Codex, OpenCode from felinics/Autofish. It costs 684 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Autofish, an Android device-control service and command-line tool for RhinoPi X1 devices. They describe the project structure, preferred and fallback execution paths, compatibility rules, and release requirements.

In plain words
What is it for?
Use them when changing Autofish's Android service, HTTP API, command-line interface, device-control routing, or skill packaging.
Why use it?
They give coding agents the project context and constraints needed to make safe changes. They also help preserve fallback behavior and keep packaged skills and documentation aligned.

Instructions file for CodexOpenCode

113 +1 4d ago A scan 684 tokens original Apache-2.0
View the source file felinics/Autofish
Install

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.

agentmods
npx agentmods add instructions/felinics/autofish/agents-md
Clone the repo
git clone --depth 1 https://github.com/felinics/Autofish

Made for: Codex, OpenCode.

Per session 684 This file is loaded in full into every session.
When invoked 684 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00684 $0.00684
Opus 5 $0.00342 $0.00342
Sonnet 5 $0.00137 $0.00137
Haiku 4.5 $0.00068 $0.00068

Measured 3d ago against content hash ce1b317045ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Autofish AGENTS.md scanned grade A with 0 findings 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 3d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project

Autofish is an Android device control service and CLI, targeting RhinoPi X1 (Qualcomm QCS8550 ARM64).

Context

  • Read docs/ARCHITECTURE.md before making architecture-impacting changes.
  • Treat the current codebase and documented release workflow as the source of truth when docs drift.

Current Baseline

  • Service/API:
    • Android foreground service: ServiceServerService
    • HTTP surface: /api/*
  • Execution path:
    • Preferred: Shizuku + system/shell path
    • Fallback: accessibility path
    • Routing entry: ToolRouter
  • CLI:
    • Current CLI UX may evolve for AX when changes are documented and versioned.
  • Skill packaging:
    • Canonical skill path: cli/skills/autofish-control/SKILL.md
    • CLI release workflow packages that exact path

Rules

  • Respond in Simplified Chinese.
  • Use just instead of make.
  • Do not add features that are not reflected in design or release docs.
  • Hidden API reflection calls must have try-catch plus runnable fallback behavior.
  • Preserve fallback execution paths when preferred capabilities are unavailable.

Compatibility Policy

  • Default to preserving external compatibility for service APIs, CLI commands, and packaged skill paths.
  • Breaking changes are allowed only when they are intentional and governed.
  • For breaking CLI or packaging changes, update docs in the same change set:
    • docs/ when design or architecture intent changes
    • CHANGELOG.md with explicit BREAKING notes
    • command migration examples when flags, command shape, or workflow changes
  • Breaking release cadence must follow semantic versioning discipline:
    • no silent breaking changes in patch releases
    • use prerelease tags such as -rc when validating release candidates

Change Process

  • If the requested change is not covered by current docs, update the relevant docs first or in the same change set.
  • Internal refactors must keep behavior coherent and keep fallback paths runnable.
  • CLI AX work may reshape command syntax when it materially improves usability, but the change must be documented and migration-ready.
  • If the skill directory or skill filename changes, update .github/workflows/cli-release.yml in the same change.

Read the full file on GitHub · 76 lines

Changes

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.

  1. 3d ago First seen · 76 lines · 684 tokens per session scan A ce1b317045ef

Subscribe to this mod's changes

Autofish AGENTS.md is an instructions file published in the GitHub repository felinics/Autofish (113 stars, last pushed 4d ago), licensed Apache-2.0. It adds 684 tokens to every session, about $0.0034 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Hardware and IoTLLMMobileai-agentandroidandroid-automationmobile-automation
Related

Other instructions, from other repositories

androir-mcp CLAUDE.md

Claude Code instructions for benasbarciauskas/androir-mcp, covering androir-mcp, scope guardrail (enforced), conventions and security.

benasbarciauskas/androir-mcp · 271 tokens

scrcpy-mcp AGENTS.md

Instructions for JuanCF/scrcpy-mcp, covering agents.md, project overview, project documentation, build/lint/test commands and build the project.

JuanCF/scrcpy-mcp · 1,693 tokens

android-agent CLAUDE.md

Instructions for ghost-in-the-droid/android-agent, covering ghost in the droid — agent tool rules, mcp tool: opencamera, mcp tool: speaktext and general rule.

ghost-in-the-droid/android-agent · 324 tokens

OpenGUI CLAUDE.md

Claude Code instructions for Core-Mate/OpenGUI, covering opengui release - repository guide for claude code / codex, 1. repository positioning, 2. default working rules, 3. high-level architecture and 4. directory map.

Core-Mate/OpenGUI · 2,471 tokens

OpenGUI AGENTS.md

AGENTS.md instructions for Core-Mate/OpenGUI: CLAUDE.md is the single source of truth for AI collaboration rules in this repository.

Core-Mate/OpenGUI · 210 tokens

lazy_mobile_mcp AGENTS.md

AGENTS.md instructions for leaf76/lazy_mobile_mcp, covering agents.md, purpose and scope, language, repo snapshot and public tools (contract).

leaf76/lazy_mobile_mcp · 2,621 tokens