Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/obviousworks/vibe-coding-ai-rules/copilot-instructionsgit clone --depth 1 https://github.com/obviousworks/vibe-coding-ai-rulesWrote 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/obviousworks/vibe-coding-ai-rules/copilot-instructions)<a href="https://agentmods.dev/instructions/obviousworks/vibe-coding-ai-rules/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/obviousworks/vibe-coding-ai-rules/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00424 | $0.00424 |
| Opus 5 | $0.00212 | $0.00212 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
vibe-coding-ai-rules 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 4d 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.
What it actually says
{{PROJECT_NAME}}
Project Overview
{{PROJECT_DESCRIPTION}}
Architecture: {{ARCHITECTURE_TYPE}} Language: {{PRIMARY_LANGUAGE}} ({{LANGUAGE_VERSION}}) Framework: {{PRIMARY_FRAMEWORK}}
Tech Stack
- Frontend: {{FRONTEND_FRAMEWORKS}}
- Backend: {{BACKEND_FRAMEWORKS}}
- Database: {{DATABASE}}
- Testing: {{TESTING_FRAMEWORK}}
- Package Manager: {{PACKAGE_MANAGER}}
DO NOT Use
- {{BANNED_DEPENDENCY_1}} (use {{ALTERNATIVE_1}} instead)
- {{BANNED_DEPENDENCY_2}} (use {{ALTERNATIVE_2}} instead)
Core Principles
- Clarify Before Coding: Understand requirements before writing code. Ask questions when intent is unclear. No code without clear goals.
- Simplicity First: Choose the simplest viable solution. Complex patterns need explicit justification. Readable code over clever code.
- Security By Default: Validate all inputs. No secrets in code. Defense in depth. Least privilege principle.
- Test-Driven Thinking: Design all code to be testable from inception. Write tests alongside code. Verify before committing.
Setup Commands
{{INSTALL_COMMAND}}
{{DEV_COMMAND}}
{{TEST_COMMAND}}
{{BUILD_COMMAND}}
Workflow
- Atomic changes: small, self-contained modifications
- Conventional commits:
type(scope): description - Only modify files directly related to the current task
- Never add new dependencies without explicit approval or compelling justification
- Use file-scoped commands. Reference docs instead of pasting. Optimize context window usage.
- Follow established conventions for the relevant language and tech stack
- Comment only complex logic or critical functions. Avoid documenting the obvious.
- After generating code, argue against your own solution. Check for redundancy, unnecessary complexity, or simpler alternatives.
When Uncertain
- Ask clarifying questions before implementing
- Reference existing patterns in the codebase
- Start small and iterate
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.
- 4d ago First seen · 51 lines · 424 tokens per session scan A 905be5f7dcfd
vibe-coding-ai-rules copilot-instructions.md is an instructions file published in the GitHub repository obviousworks/vibe-coding-ai-rules (88 stars, last pushed 2mo ago), licensed MIT. It adds 424 tokens to every session, about $0.0021 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
n.codes AGENTS.md
Instructions for yungookim/n.codes, covering repository guidelines, core architecture principle: agentic ui generation, project structure & module organization, cli module organization (cli/lib/) and build, test, and development commands.
n.codes CLAUDE.md
Instructions for yungookim/n.codes, a project described as: Let users generate features with prompts in your app.
Vibe-Coding-Dev-Setup general.instructions.md
Instructions for AndreasKarz/Vibe-Coding-Dev-Setup, covering trust boundary, project general coding standards, application structure, architecture overview and technology stack.
Vibe-Coding-Dev-Setup tests.instructions.md
Instructions for AndreasKarz/Vibe-Coding-Dev-Setup, covering general guidelines, test naming conventions, test data and setup, test structure and assertions.
Vibe-Coding-Dev-Setup graphql.instructions.md
Instructions for AndreasKarz/Vibe-Coding-Dev-Setup, covering graphql layer rules, layer separation, implementation-first approach, attribute stacking order and dataloader convention.
Vibe-Coding-Dev-Setup worker.instructions.md
Instructions for AndreasKarz/Vibe-Coding-Dev-Setup, covering worker layer rules, consumer design, observability, error handling and quartz jobs.