vakt: Instructions file for Codex

AGENTS.md

vakt AGENTS.md is an instructions file for Codex, OpenCode from osloer-industries/vakt. It costs 3,538 tokens per session, scanned C, original, MIT.

Project-specific development instructions for vakt, a TypeScript and Bun application that manages tools and policies for AI coding tools. They describe its architecture, libraries, commands, and coding rules.

In plain words
What is it for?
Use them when developing vakt features, especially its CLI, MCP proxy, configuration parsing, validation, secrets handling, and tests.
Why use it?
They give an agent the conventions and constraints needed to make changes that fit the vakt codebase.

Instructions file for CodexOpenCode

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

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is load '../test_helper'.

Reuse

Borrowing it

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

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 vakt AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/osloer-industries/vakt/agents-md.svg)](https://agentmods.dev/instructions/osloer-industries/vakt/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/osloer-industries/vakt/agents-md"><img src="https://agentmods.dev/badge/instructions/osloer-industries/vakt/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,538 This file is loaded in full into every session.
When invoked 3,538 The same file — it is already loaded in full.
Security scan C 2 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 $0.03538 $0.03538
Opus 5 $0.01769 $0.01769
Sonnet 5 $0.00708 $0.00708
Haiku 4.5 $0.00354 $0.00354

Measured 7d ago against content hash 3d5eb3d0a512, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

vakt AGENTS.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

| `bun` | Runtime, bundler, test runner | `curl -fsSL https://bun.sh/install \| bash` |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `bun` | Runtime, bundler, test runner | `curl -fsSL https://bun.sh/install \| bash` |
AGENTS.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Development Guidelines for vakt

Project Overview

vakt is an enterprise MCP server and skills manager that syncs approved servers and policies across all AI coding tools (Claude Code, Cursor, Windsurf, Gemini CLI, Codex, OpenCode). It provides central policy, secrets management, audit logging, a skills registry, and supply chain verification — with zero infrastructure overhead.

Language: TypeScript + Bun

vakt is written in TypeScript, compiled and run with Bun. No Python. No shell scripts in src/ except src/vakt.sh (CLI shim) and src/lib/secrets.sh (legacy bash backend).

  • All source code in src/ is .ts
  • Bun is the runtime, test runner, and bundler
  • Zod is the schema/validation library — all external data must be parsed through a Zod schema before use
  • commander handles the CLI surface
  • smol-toml for TOML parsing (Codex provider)
  • @modelcontextprotocol/sdk for the MCP proxy
  • @opentelemetry/sdk-node + @opentelemetry/api for OTel spans
  • @e2b/code-interpreter for cloud runtime

Required toolchain

Tool Purpose Install
bun Runtime, bundler, test runner curl -fsSL https://bun.sh/install | bash
bats End-to-end CLI tests brew install bats-core
bun run dev                                           # run from source
bun build src/index.ts --compile --outfile dist/vakt  # single binary
bun test tests/unit/                                  # unit tests
bats tests/e2e/                                       # e2e tests
bun test tests/unit/ && bats tests/e2e/               # full suite

Architecture

  • src/index.ts — CLI entry point (commander), registers all commands
  • src/providers.json — provider registry (data-driven, validated by ProvidersSchema)
  • src/vakt.sh — thin shim: exec bun run src/index.ts "$@"
  • src/commands/ — one file per top-level command (add-server, add-skill, sync, list, …)
  • src/daemon/ — background process manager and IPC server
  • src/lib/ — shared libraries (pure functions, no CLI side effects)
  • tests/e2e/ — bats end-to-end tests (invoke the vakt CLI directly)
  • skills/ — bundled skills (bash scripts + SKILL.md)
  • install.sh — install script

Read the full file on GitHub · 310 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 · 310 lines · 3,538 tokens per session scan C 3d5eb3d0a512

Subscribe to this mod's changes

vakt AGENTS.md is an instructions file published in the GitHub repository osloer-industries/vakt (3 stars, last pushed 28d ago), licensed MIT. It adds 3,538 tokens to every session, about $0.0177 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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

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 · 5,182 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

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

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

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

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