agentmods.dev

droid-ai-toolkit AGENTS.md

droid-ai-toolkit AGENTS.md is an instructions file for Codex, OpenCode from niyazmft/droid-ai-toolkit. It costs 4,194 tokens per session, scanned A, original, MIT.

Repository instructions for Droid AI Toolkit, a Bash-based installation toolkit designed for Android and Termux.

In plain words
What is it for?
They help agents modify the installer, run JavaScript, CSS, Markdown, and shell checks, and work safely with the toolkit's Android context.
Why use it?
They explain the lint checks, safe update process, and Android-specific restrictions so agents do not overwrite device patches or skip the quality gate.

Instructions file for CodexOpenCode

not rated 21 +1 changed today A scan 4,194 tokens original MIT
View the source file niyazmft/droid-ai-toolkit
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/niyazmft/droid-ai-toolkit/agents-md
Clone the repo
git clone --depth 1 https://github.com/niyazmft/droid-ai-toolkit

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for droid-ai-toolkit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/niyazmft/droid-ai-toolkit/agents-md.svg)](https://agentmods.dev/instructions/niyazmft/droid-ai-toolkit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/niyazmft/droid-ai-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/niyazmft/droid-ai-toolkit/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,194 This file is loaded in full into every session.
When invoked 4,194 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.04194 $0.04194
Opus 5 $0.02097 $0.02097
Sonnet 5 $0.00839 $0.00839
Haiku 4.5 $0.00419 $0.00419

Measured today against content hash 99e8d22f952c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

droid-ai-toolkit 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.

| Hermes | curl installer from `hermes-agent.nousresearch.com` + automatic wheel-cache (`~/.hermes/wheel-cache`) for fast reinstalls | ❌ Not supported on `armv8l`/`armv7l` (maturin/jiter incompatibility) |
AGENTS.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Droid AI Toolkit — Agent Instructions

Project Type

Bash scripting toolkit. Main deliverable is install.sh. No app runtime here — package.json is lint-only infrastructure.

Toolchain & Commands

pnpm install               # Install linter deps ([email protected] enforced via packageManager field)
pnpm run lint:all          # Full lint gate: ESLint → Stylelint → Markdownlint → shellcheck (read-only, does NOT --fix)
python3 scripts/self_heal.py  # Strips unused `catch (err)` params from JS/MJS only
  • Lint config: eslint.config.mjs (flat/v10, Node/browser/jest globals), .stylelintrc.json (Tailwind-aware), .markdownlint.json (line length & inline HTML allowed), .shellcheckrc (bash linting).
  • CI (lint.yml) runs on Node 22 and blocks PRs to main/master.

Quality Gate & Workflow

  1. Pre-commit (npx lint-staged) auto-fixes staged *.{js,mjs}, *.css, and *.md.
  2. Run pnpm run lint:all locally before pushing; it is the PR gate.
  3. Do not assume lint:all auto-fixes — it reports only.

Android / Termux Context

  • Never use native update commands (openclaw update, etc.) — they overwrite Android patches.
  • Safe update path: re-run install.sh, choose [R] Repair (2-second patch-only) or [U] Update (latest verified version).
  • UI Engine: v1.13.0+ uses gum (charm.sh) for color-rich, touch-friendly menus with visual separators; falls back to whiptail if unavailable. ensure_deps auto-installs gum.
  • Uses $PREFIX dynamically; never hardcode /data/data/com.termux/files/usr.
  • Memory guard: Node.js heap limit is set to min(2048, max(512, RAM * 0.75)) via --max-old-space-size.
  • PM2 is killed during updates to prevent OOM on low-RAM devices.
  • Zero-latency navigation: v1.13.0+ caches Bash variables for get_config and pnpm_root_g, and eliminates redundant Node.js / jq spawns during menu rendering.
  • Koffi kernel patch: renameat2 → rename to avoid kernel crashes.
  • Gemini CLI patch: fs.promises.rename → copyFile + unlink to avoid Android ENOENT.

Read the full file on GitHub · 156 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. today Changed · +15 lines · +842 tokens per session 99e8d22f952c
  2. 5d ago First seen · 141 lines · 3,352 tokens per session scan A 50f49b69ca33

Subscribe to this mod's changes

droid-ai-toolkit AGENTS.md is an instructions file published in the GitHub repository niyazmft/droid-ai-toolkit (21 stars, last pushed today), licensed MIT. It adds 4,194 tokens to every session, about $0.0210 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.

agentic-aiai-gatewayandroidautomationmigopenclaw
Related

Other instructions, from other repositories

agent-skills-standard agent-skill-standard-rule.instructions.md

Rule for Agent Skills Standard - Always consult AGENTS.md for consolidated project context and technical triggers.

HoangNguyen0403/agent-skills-standard · 491 tokens

agent-skills-standard CLAUDE.md

Claude Code instructions for HoangNguyen0403/agent-skills-standard, covering agent protocol and self-learning protocol.

HoangNguyen0403/agent-skills-standard · 93 tokens

claudeclaw CLAUDE.md

Instructions for sbusso/claudeclaw, covering claudeclaw, entry points, modes, directory = instance and architecture.

sbusso/claudeclaw · 3,201 tokens

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).

PatilShreyas/debroid · 606 tokens

clawock AGENTS.md

AGENTS.md instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.

KCNyu/clawock · 2,140 tokens

clawock CLAUDE.md

Claude Code instructions for KCNyu/clawock, covering claude.md, identity & user, required reads (every session, in order), what lives where and cron run loop (what openclaw fires).

KCNyu/clawock · 867 tokens