What is Network-AI copilot-instructions.md?

A GitHub Copilot instruction file for the Network-AI TypeScript and Node.js project. It records the project architecture, coding conventions, security requirements, and important files.

Use it when adding or changing orchestrator features, adapters, public APIs, security code, audit logging, or exported TypeScript code.

It tells the coding assistant how shared state, permissions, adapters, audit logs, validation, and dependencies must be handled.

Network-AI copilot-instructions.md — Instructions file by Jovancoding

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/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/Jovancoding/Network-AI

Made for: GitHub Copilot.

Per session 1,120 This file is loaded in full into every session.

When invoked 1,120 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.

Model	Per session	Once invoked
Fable 5	$0.01120	$0.01120
Opus 5	$0.00560	$0.00560
Sonnet 5	$0.00224	$0.00224
Haiku 4.5	$0.00112	$0.00112

Measured 2d ago against content hash 451f0d45c838, 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 copilot-instructions.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.

.github/copilot-instructions.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.

GitHub Copilot Instructions for Network-AI

Project Overview

Network-AI is a TypeScript/Node.js multi-agent orchestrator — shared state, guardrails, budgets, and cross-framework coordination (v5.15.1). 3,638 tests across 41 suites.

Architecture

Blackboard pattern: All coordination via LockedBlackboard — propose() → validate() → commit() with filesystem mutex. Never write to shared state directly.
Permission gating: AuthGuardian uses weighted scoring (justification 40%, trust 30%, risk 30%). Require permission before sensitive resource access.
Adapter system: All 32 adapters extend BaseAdapter. Each is dependency-free (BYOC — bring your own client). No cross-adapter imports.
Audit trail: Every write, permission grant, and state transition is logged to data/audit_log.jsonl via SecureAuditLogger.

Code Conventions

TypeScript strict mode, target ES2022
No any types — use proper generics or unknown
JSDoc on all exported functions and classes
No new runtime dependencies without explicit approval
Input validation required on all public API entry points
Keep adapter files self-contained — no cross-adapter imports

Key Files

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/fsm-journey.ts — JourneyFSM behavioral control plane
lib/compliance-monitor.ts — Real-time agent behavior surveillance
lib/adapter-hooks.ts — AdapterHookManager lifecycle hooks + matcher-based filtering
lib/skill-composer.ts — SkillComposer meta-operations (chain/batch/loop/verify)
lib/semantic-search.ts — SemanticMemory BYOE vector store
lib/phase-pipeline.ts — PhasePipeline multi-phase workflows with approval gates
lib/confidence-filter.ts — ConfidenceFilter multi-agent result scoring and filtering
lib/fan-out.ts — FanOutFanIn parallel agent spawning with pluggable aggregation
lib/mcp-transport-http.ts — McpStreamableServer MCP 2025-03-26 Streamable HTTP + resources/prompts
lib/agent-runtime.ts — AgentRuntime sandboxed execution with SandboxPolicy, ShellExecutor, FileAccessor, ApprovalGate, SourceProtectionError
lib/env-manager.ts — EnvironmentManager: promotion chain dev→st→sit→qa→preprod→prod, backup/restore, env diff, NETWORK_AI_ENV routing
lib/console-ui.ts — ConsoleUI interactive terminal dashboard
lib/strategy-agent.ts — StrategyAgent meta-orchestrator with AgentPool, WorkloadPartitioner, adaptive scaling
lib/goal-decomposer.ts — GoalDecomposer, TeamRunner, runTeam: LLM-powered goal → task DAG → parallel execution
lib/circuit-breaker.ts — CircuitBreaker CLOSED/OPEN/HALF_OPEN state machine; CircuitOpenError; wired into AdapterRegistry per-adapter with fallbackChain
lib/telemetry-provider.ts — ITelemetryProvider BYOT interface; NullTelemetryProvider, CapturingTelemetryProvider; createOtelHooks() factory for AdapterHookManager
lib/claude-hooks.ts — ClaudeHookBridge: AuthGuardian-gated coding-agent tool calls (Claude Code PreToolUse/PostToolUse), observe/enforce modes, network-ai hook CLI
lib/mcp-elicitation.ts — StdioElicitationChannel + createElicitationApprovalCallback: native in-client approval prompts over MCP elicitation (fail closed)
lib/a2a-server.ts — A2AServer: expose the orchestrator as a Google A2A agent (agent card + tasks/send, Bearer-gated)
lib/context-composer.ts — ContextComposer: token-budgeted, relevance-ranked context assembly; estimateTokens()
lib/mcp-tools-context.ts — ContextMcpTools: context_pack + blackboard_search MCP tools
adapters/ — 32 framework adapters (LangChain, AutoGen, CrewAI, MCP, Codex, Gemini, OpenAI Responses, Claude Agent SDK, MiniMax, NemoClaw, APS, Hermes, Orchestrator, etc.)

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.

2d ago First seen · 69 lines · 1,120 tokens per session scan A 451f0d45c838

Subscribe to this mod's changes

Network-AI copilot-instructions.md is an instructions file published in the GitHub repository Jovancoding/Network-AI (72 stars, last pushed 8d ago), licensed MIT. It adds 1,120 tokens to every session, about $0.0056 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.

CrewAI Data and AI Planning Security agent-framework agent-orchestration ai-agents autogen blackboard

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

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

Network-AI copilot-instructions.md