What is SerpentStack copilot-instructions.md?

Project-specific instructions for SerpentStack, a command-line tool that finds and installs AI-agent skills and servers, plus a full-stack project template. They describe its code structure, conventions, and main commands.

Use them when developing the SerpentStack command-line tool, its FastAPI and React template, or its background-agent features.

They help an agent make changes that fit SerpentStack's existing architecture and rules.

How Benja-Pauls/SerpentStack configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to Benja-Pauls/SerpentStack. 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/Benja-Pauls/SerpentStack/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/Benja-Pauls/SerpentStack

Made for: GitHub Copilot.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/benja-pauls/serpentstack/copilot-instructions/github.svg)](https://agentmods.dev/instructions/benja-pauls/serpentstack/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/benja-pauls/serpentstack/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/benja-pauls/serpentstack/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/benja-pauls/serpentstack/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/benja-pauls/serpentstack/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 770 This file is loaded in full into every session.

When invoked 770 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00770	$0.00770
Opus 5.5	$0.00308	$0.00308
Sonnet 5.5	$0.00154	$0.00154
Haiku 4.5	$0.00077	$0.00077

Measured 1mo ago against content hash 912fa20dca39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SerpentStack 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 1mo 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SerpentStack — GitHub Copilot Instructions

You are working on SerpentStack, a CLI that searches for AI agent skills and MCP servers across every major registry. It also includes a production fullstack template (FastAPI + React + PostgreSQL + Terraform) and persistent background agents.

CLI Architecture

The CLI (cli/) is the primary product. It has zero npm dependencies — Node.js built-ins only.

cli/
  bin/serpentstack.js       # Entry point, argument parsing, command routing
  lib/
    commands/
      search.js             # Cross-registry skill + MCP server search
      add.js                # Install skills from any source
      discover.js           # Project-aware recommendations (detects stack, queries registries)
      skills-init.js        # Download base skills
      skills-update.js      # Update base skills
      persistent.js         # Persistent agent setup + management
      notifications.js      # View agent findings
      stack-new.js          # Scaffold new project from template
      stack-update.js       # Update template files
    utils/
      registries.js         # Registry adapters (Anthropic, skills.sh, awesome, GitHub, MCP)
      ui.js                 # Terminal formatting, colors, spinners, branded output
      config.js             # Project detection and config management
      models.js             # Ollama model detection and management
      agent-utils.js        # OpenClaw workspace management
      github.js             # GitHub API helpers
      fs-helpers.js         # File system utilities

Key Conventions

CLI

Zero dependencies — use only Node.js built-ins (fetch, fs, path, readline, etc.)
All registry adapters return { name, source, type, description, url, install, stars?, author?, _score }[]
type is either 'skill' or 'mcp'
Scoring: 0-100 relevance score with source-weighted multipliers
Results are deduplicated by normalized name within each type (skills and MCP are separate)
MCP server entries include mcpUrl for the install command and tags for scoring
UI uses the snake brand (green theme, printHeader(), divider(), spinner())

Read the full file on GitHub · 70 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.

1mo ago First seen · 70 lines · 770 tokens per session scan A 912fa20dca39

Subscribe to this mod's changes

SerpentStack copilot-instructions.md is an instructions file published in the GitHub repository Benja-Pauls/SerpentStack (2 stars, last pushed 6mo ago), licensed MIT. It adds 770 tokens to every session, about $0.0031 per session on Opus 5.5. 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.

Claude Code agent-skills ai cli codex developer-tools

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 · 9,715 tokens

SerpentStack: Instructions file for GitHub Copilot

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

SerpentStack — GitHub Copilot Instructions

CLI Architecture

Key Conventions

CLI

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

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

langchain AGENTS.md

vscode copilot-instructions.md

deno copilot-instructions.md