secure-vibe AGENTS.md

secure-vibe AGENTS.md is an instructions file for Codex, OpenCode from ShieldNet-360/secure-vibe. It costs 1,449 tokens per session, scanned A, original, MIT.

A project instruction file for SecureVibe, a security knowledge library used by AI coding assistants. It explains contributor rules, permitted AI use, and where the generated instruction bundle is stored.

In plain words
What is it for?
Use it when contributing security rules, vulnerability information, secret-detection patterns, compliance mappings, or regenerated agent instructions.
Why use it?
It helps contributors follow the repository's human-review and security requirements, including the distinction between contribution instructions and the shipped bundle.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/shieldnet-360/secure-vibe/agents-md
Clone the repo
git clone --depth 1 https://github.com/ShieldNet-360/secure-vibe

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 secure-vibe AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shieldnet-360/secure-vibe/agents-md.svg)](https://agentmods.dev/instructions/shieldnet-360/secure-vibe/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/shieldnet-360/secure-vibe/agents-md"><img src="https://agentmods.dev/badge/instructions/shieldnet-360/secure-vibe/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,449 This file is loaded in full into every session.
When invoked 1,449 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01449 $0.01449
Opus 5 $0.00724 $0.00724
Sonnet 5 $0.00290 $0.00290
Haiku 4.5 $0.00145 $0.00145

Measured 3d ago against content hash 4e22a75a16d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

secure-vibe 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 3d 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 · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for SecureVibe (secure-vibe)

[!NOTE] This AGENTS.md is the contribution policy for the SecureVibe source repository. It is not the file you ship to your own project. If you came here looking for the compiled bundle of security skills that Codex / OpenAI agents drop into a consumer repo, that file lives at dist/AGENTS.md and is regenerated by secure-vibe dev regenerate.

[!IMPORTANT] This project does not accept pull requests that are fully or predominantly AI-generated. AI tools may be used solely in an assistive capacity, with explicit disclosure in the PR description.

The full contributor workflow is in CONTRIBUTING.md.

SecureVibe is a security knowledge library. Its detection rules, vulnerability database, secret-detection patterns, and compliance mappings are relied on by AI coding assistants to make security decisions for real users. Every entry must therefore be authored, reviewed, and defensible by a human contributor. AI-generated entries that no human can explain or justify are not acceptable — even if the syntax validates and CI is green.


Guidelines for contributors using AI

The following uses of AI are permitted when contributing to SecureVibe:

  • Asking AI to explain the structure of the codebase or the layout of an existing skill.
  • Asking AI to point you at relevant documents, links, advisories, or upstream sources.
  • Asking AI to review code or rules you have already written and suggest improvements.
  • Expanding on a verbose change you have already conceptualized — for example, generating repeated lines with minor variations (only for short snippets where deduplication would add more complexity than the duplication), or formatting for consistency.
  • Completing short code or YAML segments based on a pattern already established in the surrounding file (e.g., filling in the third tags: entry once two are written).
  • Drafting documentation prose for a component you are already familiar with.

Read the full file on GitHub · 166 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. 3d ago First seen · 166 lines · 1,449 tokens per session scan A 4e22a75a16d6

Subscribe to this mod's changes

secure-vibe AGENTS.md is an instructions file published in the GitHub repository ShieldNet-360/secure-vibe (22 stars, last pushed 20d ago), licensed MIT. It adds 1,449 tokens to every session, about $0.0072 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.