Borrowing it
Nothing to install: this file belongs to roedyrustam/vibes-plug. 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/roedyrustam/vibes-plug/main/AGENTS.mdgit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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/roedyrustam/vibes-plug/agents-md)<a href="https://agentmods.dev/instructions/roedyrustam/vibes-plug/agents-md"><img src="https://agentmods.dev/badge/instructions/roedyrustam/vibes-plug/agents-md/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/roedyrustam/vibes-plug/agents-md"><img src="https://agentmods.dev/badge/instructions/roedyrustam/vibes-plug/agents-md.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 | $0.04403 | $0.04403 |
| Opus 5.5 | $0.01761 | $0.01761 |
| Sonnet 5.5 | $0.00881 | $0.00881 |
| Haiku 4.5 | $0.00440 | $0.00440 |
Grade A, and why
vibes-plug AGENTS.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 today.
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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Rule for Vibes-Plug Agents
🌐 Universal Compatibility: These rules apply to ALL AI platforms using vibes-plug: Antigravity (AGY) via
AGENTS.md| Claude Code viaCLAUDE.md+.claude/rules/| Cursor IDE via.cursorrules+.cursor/rules/| OpenAI Codex viaCODEX.md+.codex/rules/Each platform has its own entry point, but the core rules and 176 skills are shared.
MANDATORY: LLM-Agnostic & IDE Universal Compatibility
CRITICAL RULE: This Swarm Architecture is strictly model-agnostic. It is engineered to extract maximum reasoning capabilities from ALL Latest Frontier Models across all IDE tiers:
- High Fast / Low-Latency Tier: xAI Grok 4.7 High Fast / Grok 4.6 High Fast (sub-second TTFT, real-time web compute, lightning test iterations), Cursor Composer 2.5 Fast (native multi-file diff engine & fast refactoring).
- Medium / Balanced Tier: Google Gemini 4 Argon Medium (2M+ monolithic context, native caching), OpenAI GPT-5.6 Sol Medium (strict tool calling & structured contracts), Anthropic Claude Opus 5.5 Medium (balanced deep architectural comprehension).
- High / Extended Thinking Tier: Anthropic Claude Sonnet 5.5 High (flagship fullstack reasoning & extended thinking), Anthropic Claude Fable 5.1 High (prompt-cache optimized agentic workflows), Muse Wonder High (exploratory reasoning & generative design synthesis), Google Gemini 4 Pro / Project Astra, and DeepSeek-R1 / Pro / V3. The AI MUST adapt the orchestration payload according to its native context window, execution tier, and thinking budget.
MANDATORY: Availability Fallback Invariant (Invarian Pengalihan Ketersediaan)
When a frontier model is not yet provisioned, reaches rate/quota limits, or is temporarily unavailable in the user's environment:
- Gemini 4 Fallback (Argon & Pro): Automatically and seamlessly degrade tasks to
Gemini 3.8 Flash(preserving 1M+ context window, native context caching, and sub-100ms TTFT). - Claude Opus 5.5 Fallback: Automatically and seamlessly degrade tasks to
Claude Opus 4.6(preserving deep architectural reasoning and cross-domain logic validation). - Never fail with unhandled missing-model errors or stub implementations; execute immediately through the fallback path with zero disruption.
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.
- today Changed aee824e7c107
- 2d ago Changed fb63ee138d33
- 3d ago Changed · +4 lines · +330 tokens per session 2080a4505ac0
- 5d ago Changed · +11 lines · +467 tokens per session 1ff2ac5f9df5
- 6d ago Changed · +1 lines · -2 tokens per session ab05b531eaf3
- 7d ago Changed 59fccad9bc5d
- 10d ago Changed · +8 tokens per session cb3fba25df48
- 18d ago Changed · +2 lines · +207 tokens per session 7ae99756a5df
- 20d ago Changed · +21 tokens per session 584dae9e09ae
- 21d ago First seen · 156 lines · 3,372 tokens per session scan A 5a159e73d9d4
vibes-plug AGENTS.md is an instructions file published in the GitHub repository roedyrustam/vibes-plug (114 stars, last pushed today), licensed MIT. It adds 4,403 tokens to every session, about $0.0176 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 2026-08-30.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.