agentmods.dev

AgentCall AGENTS.md

Project instructions for AgentCall, a real-time communication system with a Node.js and TypeScript server, mobile apps, and infrastructure files.

In plain words
What is it for?
Use them when changing or testing the AgentCall backend, Android or iOS apps, deployment setup, or embedded MCP endpoint.
Why use it?
They give a coding agent the project's structure, coding rules, validation requirements, and build and test commands.

Instructions file for CodexOpenCode

2 3d ago A scan 347 tokens original MIT
View the source file patil-shubham-dev/AgentCall
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/patil-shubham-dev/agentcall/agents-md
Clone the repo
git clone --depth 1 https://github.com/patil-shubham-dev/AgentCall

Made for: Codex, OpenCode.

Per session 347 This file is loaded in full into every session.
When invoked 347 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 $0.00347 $0.00347
Opus 5 $0.00173 $0.00173
Sonnet 5 $0.00069 $0.00069
Haiku 4.5 $0.00035 $0.00035

Measured 2d ago against content hash de63171a1872, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentCall 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 2d 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 · 35 lines

What it actually says

AgentCall MCP — Project Context

Stack

  • Backend: Node.js / TypeScript, Express/Fastify
  • Database: PostgreSQL 16 (or in-memory for dev)
  • WebRTC Signaling: WebSocket (Node.js)
  • STUN/TURN: coturn (self-hosted)
  • MCP Endpoint: Embedded in backend (Streamable HTTP via Fastify, MCP SDK)
  • Mobile: Android (Kotlin), iOS (Swift)
  • Deployment: Docker Compose on Hetzner VPS (manual setup first)
  • Reverse Proxy: Caddy with auto TLS

Repo Structure

/backend       — All server-side services (incl. embedded MCP endpoint)
/mobile        — Android + iOS apps
/infra         — Docker Compose, Caddyfile, coturn config
/docs          — Design documents

Conventions

  • TypeScript strict mode, no any
  • Prettier + ESLint, 2-space indent
  • Input validation at every API boundary (Zod schemas)
  • Errors: structured { error, code, details } responses
  • Commits: type(scope): description (e.g., feat(auth): add OAuth login)
  • No secrets in code, use .env (documented in .env.example)

Build & Test

  • npm run dev — starts all services in dev mode
  • npm run lint — ESLint + tsc --noEmit
  • npm test — Vitest
  • npm run test:integration — integration tests (needs Docker)
  • Migrations: Knex.js (npm run migrate)
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. 2d ago First seen · 35 lines · 347 tokens per session scan A de63171a1872

Subscribe to this mod's changes

AgentCall AGENTS.md is an instructions file published in the GitHub repository patil-shubham-dev/AgentCall (2 stars, last pushed 3d ago), licensed MIT. It adds 347 tokens to every session, about $0.0017 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 2026-08-31.

Building agentsai-agentsandroidfastifymcpmodel-context-protocolvoice-calling
Related

Other instructions, from other repositories

android-mock-location-mcp CLAUDE.md

Instructions for Manabu-GT/android-mock-location-mcp, covering claude.md, project overview, key commands, server and test connection (after emulator started).

Manabu-GT/android-mock-location-mcp · 601 tokens

android-docs-mcp AGENTS.md

Instructions for ankit-verma-209171/android-docs-mcp, covering agents.md, project overview, working agreements, source layout and build and validation.

ankit-verma-209171/android-docs-mcp · 486 tokens

sceneview AGENTS.md

Instructions for sceneview/sceneview, covering agents.md — conventions for delegated coding agents, your role, git — you do not own it, secrets and hard technical rules.

sceneview/sceneview · 1,086 tokens

llm-context.py CLAUDE.md

Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.

cyberchitta/llm-context.py · 582 tokens

openrouter-mcp-multimodal AGENTS.md

Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).

stabgan/openrouter-mcp-multimodal · 783 tokens

ntfy-mcp-server AGENTS.md

Instructions for cyanheads/ntfy-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.

cyanheads/ntfy-mcp-server · 7,551 tokens