agentmods.dev

Network-AI GEMINI.md

A GEMINI.md instruction file for Gemini CLI, a command-line coding assistant, in the Network-AI project. It explains the project, its coordination tools, and how to build and test it.

In plain words
What is it for?
Use it when Gemini CLI works on Network-AI, especially for shared agent state, permissions, usage budgets, auditing, builds, and tests.
Why use it?
It gives the coding assistant the project context and working rules needed to make coordinated, safe changes.

Instructions file for Gemini CLI

72 8d ago A scan 811 tokens original MIT
View the source file Jovancoding/Network-AI
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/jovancoding/network-ai/gemini-md
Clone the repo
git clone --depth 1 https://github.com/Jovancoding/Network-AI

Made for: Gemini CLI.

Per session 811 This file is loaded in full into every session.
When invoked 811 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 $0.00811 $0.00811
Opus 5 $0.00405 $0.00405
Sonnet 5 $0.00162 $0.00162
Haiku 4.5 $0.00081 $0.00081

Measured 2d ago against content hash 5903dd3a5126, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Network-AI GEMINI.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.

GEMINI.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEMINI.md — Project Instructions for Gemini CLI

This file is read automatically by Gemini CLI when working in this repository (and when the Network-AI extension is installed).

What Network-AI Is

Network-AI is a TypeScript/Node.js multi-agent orchestrator — shared state, guardrails, budgets, and cross-framework coordination. When installed as a Gemini CLI extension, the Network-AI MCP server loads automatically and exposes coordination tools (blackboard_read, blackboard_write, budget_status, token_create, audit_query, and more) directly inside Gemini CLI.

Using the MCP Tools

  • Blackboard — shared state between agents. Always write through blackboard_write with your agent_id; never assume exclusive access. Reads via blackboard_read / blackboard_list.
  • Budgets — budget_status before spending, budget_spend to record token usage. Respect the federated ceiling.
  • Permissions — token_create issues an HMAC/Ed25519-signed grant for a resource; token_validate checks one. Request permission before sensitive resource access.
  • Audit — every write, grant, and state transition is logged. Query with audit_query.

Build & Test Commands (when working on this repo)

npm install                   # Install dependencies
npx tsc --noEmit              # Type-check (zero errors expected)
npm run test:all              # Run the full test suite
npm test                      # Core orchestrator tests only
npm run test:adapters         # All framework adapter tests

All tests must pass before any commit. No test should be skipped or marked .only.

Project Structure

  • index.ts — Core engine: SwarmOrchestrator, AuthGuardian, FederatedBudget, QualityGateAgent
  • security.ts — SecureTokenManager, InputSanitizer, RateLimiter, DataEncryptor, SecureAuditLogger
  • lib/locked-blackboard.ts — LockedBlackboard with atomic propose → validate → commit
  • lib/auth-guardian.ts — Weighted permission scoring (justification 40%, trust 30%, risk 30%)
  • lib/a2a-server.ts — A2AServer: expose the orchestrator as a Google A2A agent (agent card + tasks)
  • adapters/ — 32 framework adapters, including GeminiAdapter (Gemini Developer API) and VertexAIAdapter (Vertex AI / Gemini on GCP)
  • bin/mcp-server.ts — the MCP server this extension launches (stdio transport)

Read the full file on GitHub · 69 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. 2d ago First seen · 69 lines · 811 tokens per session scan A 5903dd3a5126

Subscribe to this mod's changes

Network-AI GEMINI.md is an instructions file published in the GitHub repository Jovancoding/Network-AI (72 stars, last pushed 8d ago), licensed MIT. It adds 811 tokens to every session, about $0.0041 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.

CrewAIagent-frameworkagent-orchestrationai-agentsautogenblackboard
Related

Other instructions, from other repositories

kungfu CLAUDE.md

Claude Code instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before working in this repository. It routes both product use and contribution work to the repository sources of truth, including the requirement that development and build tasks enter through Shifu.

kungfu-systems/kungfu · 54 tokens

kungfu copilot-instructions.md

Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.

kungfu-systems/kungfu · 45 tokens

pi-agent-dashboard AGENTS.md

Instructions for BlackBeltTechnology/pi-agent-dashboard, covering pi dashboard, docs-first gate — kb before grep (per-turn doctrine), code instructions (per-turn doctrine), investigation protocol — index first and documentation update protocol.

BlackBeltTechnology/pi-agent-dashboard · 3,617 tokens

semantix CLAUDE.md

Instructions for Gnosil/semantix, covering 项目规则（claude code） and 1. 改动须经用户过目；由 claude 提交到分支 + pr，用户 review 后合并.

Gnosil/semantix · 301 tokens

BuildersGate CLAUDE.md

Instructions for Thepizzapie/BuildersGate, covering setting up builders gate for a user, ask two things first, install, point it at a game and keys.

Thepizzapie/BuildersGate · 1,737 tokens

designpowers GEMINI.md

Gemini CLI instructions for Owl-Listener/designpowers, covering designpowers, mandatory: welcome sequence first, skills, agents and notes for gemini cli.

Owl-Listener/designpowers · 569 tokens