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

.github/instructions/autonomous-development.instructions.md

mcp-vibe-coding-tools autonomous-development.instructions.md is an instructions file for GitHub Copilot from ammilam/mcp-vibe-coding-tools. It costs 2,671 tokens per session, scanned A, original, MIT.

Instructions for letting an AI agent carry out software development tasks from planning through validation without routine human approval. They define a workflow for understanding requirements, writing code, testing, and checking the result.

In plain words
What is it for?
For handling coding tasks end to end, including planning, implementation, error handling, logging, tests, documentation, and automatic checks.
Why use it?
They reduce the need to supervise each development step and make validation part of the normal workflow.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is ammilam/mcp-vibe-coding-tools's own configuration. It tells GitHub Copilot how to work on mcp-vibe-coding-tools 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 mcp-vibe-coding-tools configures →

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/autonomous-development.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.

agentmods badge for mcp-vibe-coding-tools autonomous-development.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ammilam/mcp-vibe-coding-tools/autonomous-development/github.svg)](https://agentmods.dev/instructions/ammilam/mcp-vibe-coding-tools/autonomous-development)
Your own site
<a href="https://agentmods.dev/instructions/ammilam/mcp-vibe-coding-tools/autonomous-development"><img src="https://agentmods.dev/badge/instructions/ammilam/mcp-vibe-coding-tools/autonomous-development/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.

agentmods 80×15 button for mcp-vibe-coding-tools autonomous-development.instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ammilam/mcp-vibe-coding-tools/autonomous-development"><img src="https://agentmods.dev/badge/instructions/ammilam/mcp-vibe-coding-tools/autonomous-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,671 This file is loaded in full into every session.
When invoked 2,671 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02671 $0.02671
Opus 5.5 $0.01068 $0.01068
Sonnet 5.5 $0.00534 $0.00534
Haiku 4.5 $0.00267 $0.00267

Measured 2mo ago against content hash daf4283f4851, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-vibe-coding-tools autonomous-development.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 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/autonomous-development.instructions.md · 418 lines

How it starts

The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Development Instructions

Core Principle: Zero Human Intervention

You are empowered to operate fully autonomously. Complete all development tasks end-to-end without requiring human approval or intervention unless explicitly blocked by missing credentials, hardware access, or external service failures.

Autonomous Development Workflow

1. Understanding & Planning (Auto-Execute)

  • Analyze requirements thoroughly before writing any code
  • Break down complex tasks into discrete, testable units
  • Create implementation plan with clear success criteria
  • Document assumptions and architectural decisions upfront
  • NO APPROVAL NEEDED - proceed directly to implementation

2. Implementation (Fully Autonomous)

  • Write production-ready code on first attempt
  • Include comprehensive error handling for all edge cases
  • Add logging and observability from the start
  • Follow language/framework best practices automatically
  • Use MCP tools to validate code as you write it
  • Create tests alongside code - never defer testing
  • Generate documentation inline and in separate docs

3. Validation (Auto-Execute All Checks)

Execute ALL validation steps automatically without asking:

Code Quality:

  • Run linters (npm run lint, eslint, pylint, etc.)
  • Check code formatting (prettier, black, etc.)
  • Verify type safety (tsc --noEmit, mypy, etc.)
  • FIX ALL ISSUES IMMEDIATELY - do not report and wait

Testing:

  • Run unit tests (npm test, pytest, etc.)
  • Run integration tests if they exist
  • Check code coverage - aim for >80%
  • FIX FAILING TESTS IMMEDIATELY - iterate until green

Build Verification:

  • Compile/build the project (npm run build, cargo build, etc.)
  • Verify no build errors or warnings
  • FIX BUILD ISSUES IMMEDIATELY - do not stop until it builds

Security & Performance:

  • Run security scanners if available (npm audit, safety check, etc.)
  • Check for common vulnerabilities
  • Profile performance-critical code paths
  • FIX CRITICAL ISSUES - document minor ones

Read the full file on GitHub · 418 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. 2mo ago First seen · 418 lines · 2,671 tokens per session scan A daf4283f4851

Subscribe to this mod's changes

mcp-vibe-coding-tools autonomous-development.instructions.md is an instructions file published in the GitHub repository ammilam/mcp-vibe-coding-tools (1 stars, last pushed 9mo ago), licensed MIT. It adds 2,671 tokens to every session, about $0.0107 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.

Related

mcp-vibe-coding-tools autonomous-development.instructions.md compared with instructions from other repositories

mcp-vibe-coding-tools autonomous-development.instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-vibe-coding-tools autonomous-development.instructions.mdammilam/mcp-vibe-coding-toolsInstructions file19mo agoMITA2,671GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode