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.
curl -O https://raw.githubusercontent.com/ammilam/mcp-vibe-coding-tools/main/.github/instructions/autonomous-development.instructions.mdgit clone --depth 1 https://github.com/ammilam/mcp-vibe-coding-toolsWrote 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.
[](https://agentmods.dev/instructions/ammilam/mcp-vibe-coding-tools/autonomous-development)<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.
<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>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 | $0.02671 | $0.02671 |
| Opus 5.5 | $0.01068 | $0.01068 |
| Sonnet 5.5 | $0.00534 | $0.00534 |
| Haiku 4.5 | $0.00267 | $0.00267 |
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.
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
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 · 418 lines · 2,671 tokens per session scan A daf4283f4851
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.
mcp-vibe-coding-tools autonomous-development.instructions.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-vibe-coding-tools autonomous-development.instructions.mdammilam/mcp-vibe-coding-tools | Instructions file | 1 | 9mo ago | MIT | A | 2,671 | 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 |