What is Autonomous Development with Fundamental Tools?

A set of instructions for turning broad software requests into working products through discovery, research, construction, and checking.

Use it to explore a project, research unfamiliar requirements, write and test code, manage packages, and work with Git.

It provides a repeatable way to handle a large coding task when no single tool can do everything.

How ammilam/mcp-vibe-coding-tools configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to ammilam/mcp-vibe-coding-tools. 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/ammilam/mcp-vibe-coding-tools/main/.github/instructions/complete-development-org.instructions.md

Clone the repo

git clone --depth 1 https://github.com/ammilam/mcp-vibe-coding-tools

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/ammilam/mcp-vibe-coding-tools/complete-development-org/github.svg)](https://agentmods.dev/instructions/ammilam/mcp-vibe-coding-tools/complete-development-org)

Your own site

<a href="https://agentmods.dev/instructions/ammilam/mcp-vibe-coding-tools/complete-development-org"><img src="https://agentmods.dev/badge/instructions/ammilam/mcp-vibe-coding-tools/complete-development-org/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/ammilam/mcp-vibe-coding-tools/complete-development-org"><img src="https://agentmods.dev/badge/instructions/ammilam/mcp-vibe-coding-tools/complete-development-org.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,448 This file is loaded in full into every session.

When invoked 6,448 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	$0.06448	$0.06448
Opus 5.5	$0.02579	$0.02579
Sonnet 5.5	$0.01290	$0.01290
Haiku 4.5	$0.00645	$0.00645

Measured 2mo ago against content hash 2186a1bf7201, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Autonomous Development with Fundamental Tools 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 2mo 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/instructions/complete-development-org.instructions.md · 951 lines

How it starts

The opening of the file, as written. The whole thing — 951 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Instructions: Autonomous Software Development with Building Blocks

You have access to fundamental MCP tools that are building blocks - not prescriptive templates. Your mission is to transform high-level prompts into fully functional, production-ready software products by discovering, researching, and intelligently combining these tools.

Core Philosophy: Discover → Research → Build → Validate

Do NOT look for prescriptive "generate_X" tools. Instead, combine fundamental capabilities:

File Operations - Read, write, search, analyze project structure
Web Research - Fetch live documentation, best practices, examples
Execution - Run commands, test builds, validate functionality
Git Operations - Commit, branch, track changes
Package Management - Install dependencies, run scripts, check health

Available Tool Categories

1. Filesystem Tools (Discovery & Implementation)

read_file - Analyze existing code, configs, documentation
write_file - Create new files (code, configs, docs)
list_directory - Explore project structure
create_directory - Set up folder hierarchies
search_files - Find files by glob patterns
file_info - Get metadata about files

Use for: Project analysis, code generation, documentation, config creation

2. Command Execution Tools (Validation & Automation)

execute_command - Run any shell command
which_command - Find executable paths
get_environment - Check env vars and system info
get_terminal_history - See recent commands

Use for: Building, testing, linting, running scripts, system checks

3. Web Tools (Research & Discovery)

fetch_webpage - Get live documentation and best practices
extract_links - Find related resources
parse_html - Extract structured data from docs
download_file - Get examples, templates, binaries

Use for: Researching tech stacks, finding best practices, downloading examples

4. Git Tools (Version Control)

git_status, git_diff - Check changes
git_commit, git_push - Save work
git_branch - Manage branches
git_log - Review history
git_clone - Get example repos

Read the full file on GitHub · 951 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.

2mo ago First seen · 951 lines · 6,448 tokens per session scan A 2186a1bf7201

Subscribe to this mod's changes

Autonomous Development with Fundamental Tools is an instructions file published in the GitHub repository ammilam/mcp-vibe-coding-tools (1 stars, last pushed 9mo ago), licensed MIT. It adds 6,448 tokens to every session, about $0.0258 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.

Building agents Planning

Autonomous Development with Fundamental Tools next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Autonomous Development with Fundamental Toolsammilam/mcp-vibe-coding-tools	Instructions file	1	9mo ago	MIT	A	6,448	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-vibe-coding-tools: Instructions file for GitHub Copilot