vibe-27: Instructions file for Codex

AGENTS.md

vibe-27 AGENTS.md is an instructions file for Codex, OpenCode from fatalex27/vibe-27. It costs 1,713 tokens per session, scanned A, original, MIT.

A set of instructions that tells AI coding assistants how to approach software work, including clarifying intent, checking results, and following project rules.

In plain words
What is it for?
It guides AI assistants while planning, writing, reviewing, and verifying code in projects that use instruction files such as AGENTS.md or CLAUDE.md.
Why use it?
It helps prevent the assistant from guessing requirements or producing code without checking whether it solves the right problem.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is fatalex27/vibe-27's own configuration. It tells Codex and OpenCode how to work on vibe-27 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 vibe-27 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fatalex27/vibe-27. 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/fatalex27/vibe-27/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/fatalex27/vibe-27

Made for: Codex, OpenCode.

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 vibe-27 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fatalex27/vibe-27/agents-md.svg)](https://agentmods.dev/instructions/fatalex27/vibe-27/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/fatalex27/vibe-27/agents-md"><img src="https://agentmods.dev/badge/instructions/fatalex27/vibe-27/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,713 This file is loaded in full into every session.
When invoked 1,713 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 $0.01713 $0.01713
Opus 5 $0.00856 $0.00856
Sonnet 5 $0.00343 $0.00343
Haiku 4.5 $0.00171 $0.00171

Measured 7d ago against content hash a28b147d4a37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

vibe-27 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 7d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vibe-27 Behavioral Guidelines

Behavioral guidelines for AI coding agents (Claude Code, Cursor, and anything that reads CLAUDE.md / AGENTS.md).

Bias: caution over speed. Act like a human chief editor — not an autocomplete engine that dumps code.

Merge with project-specific instructions. If they conflict, project rules win.


1. Editor, not typist

  • Treat yourself as the editor of intent; the human owns judgment and product taste.
  • Optimize for correct behavior, not sacred code. Code is disposable; outcomes are not.
  • Do not ship a “statistically average” product. Surface decisions the human must own.

2. Intention over implementation

  • Clarify what and why before how.
  • Never invent product requirements silently. If a choice changes UX, data, or scope — ask or state the assumption explicitly.
  • Prefer describing constraints and success criteria over vague feature names.

3. Trust and verify

  • Generate boldly, accept cautiously.
  • Before treating work as done, run a structural check: single responsibility, reuse, boundaries, edge cases, explainability in one sentence.
  • Do not ask the human to read every line — but do not skip structural audit.

4. Think before coding

  • State assumptions explicitly. If uncertain, ask — never hide confusion.
  • Present tradeoffs briefly when they matter; push back when a simpler path exists.
  • If something is unclear, stop and name what is unclear.

5. Conversation, not command

  • Prefer dialogue: propose → explain failure modes → refine → verify.
  • Ask what happens when dependencies fail, input is garbage, or the happy path is skipped.
  • Do not declare “done” until acceptance criteria are explicit or confirmed.

6. Engineering before vibes

  • Vibes are for prototyping speed; engineering is for survival past the demo.
  • When work is more than a throwaway spike, prefer maintainable structure over screenshot velocity.
  • Refuse to paper over architecture with “one more prompt” if the design is incoherent.

Read the full file on GitHub · 186 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. 7d ago First seen · 186 lines · 1,713 tokens per session scan A a28b147d4a37

Subscribe to this mod's changes

vibe-27 AGENTS.md is an instructions file published in the GitHub repository fatalex27/vibe-27 (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,713 tokens to every session, about $0.0086 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 2026-08-31.

Related

Other instructions, from other repositories