vibeguard: Instructions file for Codex

AGENTS.md

vibeguard AGENTS.md is an instructions file for Codex, OpenCode from majiayu000/vibeguard. It costs 1,335 tokens per session, scanned A, original, MIT.

Repository-wide instructions for VibeGuard, a project that provides anti-hallucination rules, hooks, runtime code, installers, and workflows for coding agents. An AGENTS.md file tells agents how to work in a repository.

In plain words
What is it for?
It is for guiding changes to VibeGuard's runtime, hooks, setup scripts, workflows, documentation, and GitHub-related work.
Why use it?
It makes agents check the repository state and documentation, preserve unrelated work, follow naming and error-handling rules, and stay within the requested scope.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

This is majiayu000/vibeguard's own configuration. It tells Codex and OpenCode how to work on vibeguard 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 vibeguard configures →

Reuse

Borrowing it

Nothing to install: this file belongs to majiayu000/vibeguard. 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/majiayu000/vibeguard/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/majiayu000/vibeguard

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 vibeguard AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/majiayu000/vibeguard/agents-md.svg)](https://agentmods.dev/instructions/majiayu000/vibeguard/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/majiayu000/vibeguard/agents-md"><img src="https://agentmods.dev/badge/instructions/majiayu000/vibeguard/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,335 This file is loaded in full into every session.
When invoked 1,335 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 $0.01335 $0.01335
Opus 5 $0.00668 $0.00668
Sonnet 5 $0.00267 $0.00267
Haiku 4.5 $0.00134 $0.00134

Measured 7d ago against content hash 633d8ba622f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

vibeguard 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.

AGENTS.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Scope

This file applies to the whole repository unless a nested AGENTS.md overrides it.

VibeGuard is an anti-hallucination rules, hooks, runtime, installer, and workflow repository. There is no ORM, front-end framework, or microservices layer in this project.

Start Here

  1. Check git status --short --branch and preserve unrelated work.
  2. Search before adding files, functions, rules, hooks, workflows, or tests.
  3. Read docs/directory-map.md before moving files or changing public paths.
  4. Read docs/specs/README.md and plan/README.md before treating documents as pending work.
  5. For runtime, hook, setup, or workflow changes, read the closest scoped CLAUDE.md.
  6. For GitHub work, verify live remote state and use an isolated worktree based on the current remote base.

Core Rules

  • Keep names snake_case unless an external API boundary requires camelCase.
  • Do not swallow errors silently. User-visible missing data or wrong output must fail loudly.
  • Do only the requested scope; avoid opportunistic refactors.
  • Preserve VibeGuard's core enforcement model: rules, hooks, setup scripts, and vibeguard-runtime/ are the source implementation.
  • Treat plugin, pack, docs, and workflow changes as distribution layers unless a current design explicitly changes runtime behavior.
  • High-context files such as AGENTS.md, CLAUDE.md, .claude/settings*.json, setup scripts, hooks, and workflow contracts require explicit intent.
  • Never add AI-generated markers or hidden attribution text to commits, docs, or generated artifacts.

Delivery Policy

  • Implement clear, bounded tasks directly. Do not require a spec, routing packet, schema, receipt, runtime snapshot, or multi-agent handoff for ordinary work.
  • Clarify only when a missing choice would materially change the result or make execution unsafe.
  • Write a plan for major architecture, migration, cross-system policy work, or when the user explicitly requests one.
  • A normal spec is at most two files and about 300 lines total. Docs-only changes, small bugs, and explicit mechanical edits are spec-exempt.
  • Do not create validators for spec validators or add process artifacts merely to satisfy another process artifact.
  • Use focused tests while iterating. Run the broader relevant suite before submission; leave exhaustive platform coverage to CI.

Read the full file on GitHub · 91 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 · 91 lines · 1,335 tokens per session scan A 633d8ba622f9

Subscribe to this mod's changes

vibeguard AGENTS.md is an instructions file published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed today), licensed MIT. It adds 1,335 tokens to every session, about $0.0067 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.