copilot-engine: Instructions file for Claude Code

CLAUDE.md

copilot-engine CLAUDE.md is an instructions file for Claude Code from femitfash/copilot-engine. It costs 1,555 tokens per session, scanned A, original, MIT.

Project instructions for a reusable backend that lets an application add an AI copilot. It describes its Express server, support for different language-model providers, streaming replies, authentication, and approval of actions.

In plain words
What is it for?
Use it to develop or maintain the copilot engine, its chat and action-approval routes, tool-use loop, authentication, and separate-process deployment.
Why use it?
It gives a coding agent the project structure and operating rules needed to work safely in the codebase. It explains how the copilot runs alongside or inside another server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is femitfash/copilot-engine's own configuration. It tells Claude Code how to work on copilot-engine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything copilot-engine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to femitfash/copilot-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/femitfash/copilot-engine/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/femitfash/copilot-engine

Made for: Claude Code.

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 copilot-engine CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/femitfash/copilot-engine/claude-md.svg)](https://agentmods.dev/instructions/femitfash/copilot-engine/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/femitfash/copilot-engine/claude-md"><img src="https://agentmods.dev/badge/instructions/femitfash/copilot-engine/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,555 This file is loaded in full into every session.
When invoked 1,555 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 5.1 $0.01555 $0.01555
Opus 5 $0.00777 $0.00777
Sonnet 5 $0.00311 $0.00311
Haiku 4.5 $0.00155 $0.00155

Measured yesterday against content hash 21409e465c60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

copilot-engine CLAUDE.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 yesterday.

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.

5. **Test before completion** — run `bash tools/test.sh` (or `curl /health`) before marking work done
CLAUDE.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Engine — Claude Code Context

@claude/architecture.md @claude/conventions.md


Project Overview

Copilot Engine is a reusable, LLM-agnostic Express backend for building AI copilots. Supports Anthropic Claude and OpenAI GPT (including gpt-4.1-mini). Two deployment modes: Built-in (mounts on your existing server) or Standalone (runs as a separate process on port 3100). It handles:

  • Agentic tool-use loop (LLM calls READ tools immediately; WRITE tools are queued for user approval)
  • SSE streaming (word-by-word at ~40 words/sec)
  • Auth middleware (bearer token, session cookies, or dev header)
  • Pluggable project system (swap projects/ directory for a different domain)

The engine runs as a separate process alongside the frontend app (default port 3100).


Architecture

See @claude/architecture.md for the full data flow.

Key entry points:

  • src/index.ts — Express app, CORS, auth middleware, route mounting
  • routes/copilot.ts — POST /api/copilot (SSE chat)
  • routes/execute.ts — POST /api/copilot/execute (action approval)
  • src/engine/agentic-loop.ts — LLM-agnostic agentic loop with tool routing
  • src/engine/providers/ — LLM provider adapters (Anthropic, OpenAI)
  • src/engine/sse-stream.ts — SSE helpers (streamWords, sendDone, sendError)
  • projects/aisoar/ — AISOAR platform implementation (system-prompt, tools, tool-executor)

Tech Stack

  • Runtime: Node.js ≥ 18.0.0 (native fetch required)
  • Language: TypeScript (strict mode)
  • Framework: Express 4
  • AI: LLM-agnostic — @anthropic-ai/sdk + openai SDK. Default: Anthropic claude-sonnet-4-20250514. Host apps can implement ProjectConfig.resolveLlmConfig() to source credentials from their own per-tenant store; env vars (LLM_PROVIDER/OPENAI_API_KEY/etc., see @claude/architecture.md) are a legacy fallback for projects that don't.
  • Streaming: Server-Sent Events (SSE)
  • Auth: Bearer token / session cookies / x-copilot-auth dev header

Commands

Read the full file on GitHub · 130 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. yesterday First seen · 130 lines · 1,555 tokens per session scan A 21409e465c60

Subscribe to this mod's changes

copilot-engine CLAUDE.md is an instructions file published in the GitHub repository femitfash/copilot-engine (4 stars, last pushed 4d ago), licensed MIT. It adds 1,555 tokens to every session, about $0.0078 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 2026-09-04.

Related

Other instructions, from other repositories

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens