agentmods.dev

velobase-harness: Instructions file for Codex

AGENTS.md

velobase-harness AGENTS.md is an instructions file for Codex, OpenCode from velobase/velobase-harness. It costs 1,487 tokens per session, scanned A, original, MIT.

Project instructions for AI coding agents, including rules for routing tasks, reading the right design and integration documents, and completing required checks.

In plain words
What is it for?
Use them when building products, adding modules, changing tests, handling authentication or payments, editing email features, and finishing development checks.
Why use it?
They prevent an agent from editing sensitive parts of the project without first following the relevant guidance.

Instructions file for CodexOpenCode

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

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

not rated 598repo +8 changed yesterday A scan 1,487 tokens original MIT
View source ↗ velobase/velobase-harness velobase.cloud
Reuse

Borrowing it

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

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 velobase-harness AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/velobase/velobase-harness/agents-md.svg)](https://agentmods.dev/instructions/velobase/velobase-harness/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/velobase/velobase-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/velobase/velobase-harness/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,487 This file is loaded in full into every session.
When invoked 1,487 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 $0.01487 $0.01487
Opus 5 $0.00744 $0.00744
Sonnet 5 $0.00297 $0.00297
Haiku 4.5 $0.00149 $0.00149

Measured yesterday against content hash 5754dddb5643, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

velobase-harness 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 yesterday.

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 · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Guide

This file is the universal entry point for AI coding tools such as Cursor, Claude Code, GitHub Copilot, Windsurf, and generic agent runners.

Read this file first. Then follow the task and integration routers below before editing code.

Task Router

IF the user asks to build a new product from scratch:

  • MUST read docs/en/ai/design.md.
  • MUST complete domain design before writing product code.

IF you are about to create a new business module under src/modules/:

  • MUST read docs/en/ai/new-module.md first.

IF you are about to create or modify tests (*.test.ts, *.spec.ts, or e2e/*):

  • MUST read docs/en/ai/testing.md first.

After development is complete:

  • MUST run the checks in docs/en/ai/completion-checklist.md.
  • MUST tell the user which checks were run and which were skipped.

Integration Router

IF you touch authentication or login:

  • Read docs/en/integrations/auth/README.md.

IF you touch billing, orders, payments, subscriptions, products, credits, or promo codes:

  • Read docs/en/integrations/payment/README.md.

IF you touch email delivery or email templates:

  • Read docs/en/integrations/email/README.md.

IF you touch database, Prisma, migrations, Redis, or env-backed persistence:

  • Read docs/en/integrations/database/README.md.

IF you touch file upload, object storage, CDN URLs, or asset access:

  • Read docs/en/integrations/storage/README.md.

IF you touch analytics, feature flags, or product events:

  • Read docs/en/integrations/analytics/README.md.

IF you touch ad attribution or conversion upload:

  • Read docs/en/integrations/ads/README.md.

IF you touch queues, workers, processors, or scheduled jobs:

  • Read docs/en/integrations/queue/README.md.

IF you touch anti-abuse, captcha, rate limiting, IP, country, or security boundaries:

  • Read docs/en/integrations/security/README.md and relevant docs/en/features/*/README.md.

Core Rules

General

  • For cross-platform work, read docs/en/architecture/multiplatform.md. New host composition belongs in apps/*; process launchers in services/*; neutral schemas/clients in packages/*.
  • Desktop and Mobile must never import legacy src or Web/server packages. Platform environment configuration uses its own validated adapter, never src/env.js.

Read the full file on GitHub · 153 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. yesterday Changed · +3 lines · +75 tokens per session 5754dddb5643
  2. 9d ago First seen · 150 lines · 1,412 tokens per session scan A c48db8e63c44

Subscribe to this mod's changes

velobase-harness AGENTS.md is an instructions file published in the GitHub repository velobase/velobase-harness (598 stars, last pushed 2d ago), licensed MIT. It adds 1,487 tokens to every session, about $0.0074 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.

ai-agentai-saasbillingmonetizationnextjsopen-source
Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens