okf-skills: Instructions file for Codex

AGENTS.md

okf-skills AGENTS.md is an instructions file for Codex, OpenCode from xSAVIKx/okf-skills. It costs 3,959 tokens per session, scanned B, original, Apache-2.0.

Repository instructions for okf-skills, a collection of tools and guidance for creating, using, and publishing Open Knowledge Format bundles. A monorepo is one repository containing multiple related projects; this guide explains that repository’s structure and rules.

In plain words
What is it for?
Working on the Go modules, shared library, skills, tests, builds, and release process in okf-skills.
Why use it?
It gives a coding agent the project-specific context needed to make changes that fit the repository’s architecture and standards.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

Nothing to install: this file belongs to xSAVIKx/okf-skills. 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/xSAVIKx/okf-skills/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/xSAVIKx/okf-skills

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 okf-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xsavikx/okf-skills/agents-md/github.svg)](https://agentmods.dev/instructions/xsavikx/okf-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/xsavikx/okf-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/xsavikx/okf-skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for okf-skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/xsavikx/okf-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/xsavikx/okf-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,959 This file is loaded in full into every session.
When invoked 3,959 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.03959 $0.03959
Opus 5 $0.01980 $0.01980
Sonnet 5 $0.00792 $0.00792
Haiku 4.5 $0.00396 $0.00396

Measured 9d ago against content hash b693e3c66922, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

okf-skills AGENTS.md scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Then register `okf-mcp` as an MCP server in your harness configuration. For Claude Code (`~/.claude/settings.json`):
AGENTS.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open Knowledge Format (OKF) Skills — Developer Agent Guide

Welcome, Agent! This guide contains crucial context, structural guidelines, and best practices for working in the okf-skills repository. Follow these principles to maintain high-quality, spec-compliant, and portable implementations.


1. Repository Overview & Architecture

This repository is a central collection of skills for producing, consuming, and authoring Open Knowledge Format (OKF) bundles — standalone CLI connectors, instructions-only guidance skills (read, enrich, and author), and a generic MCP server. It is organized as a Go workspace containing multiple modules:

okf-skills/
├── AGENTS.md                      # This guide
├── README.md                      # General user-facing overview
├── CONTRIBUTING.md                # Contributor workflow & conventions
├── RELEASING.md                   # Release process (release-please lockstep versioning)
├── LICENSE                        # Apache License 2.0
├── go.work                        # Go workspace defining monorepo modules
├── Makefile                       # Build, test, install shortcuts
├── install.sh                     # Build and install all skills to a directory
├── skills.sh.json                 # skills.sh registry manifest (groups skills for discovery)
├── release-please-config.json     # release-please config (lockstep versioning)
├── .release-please-manifest.json  # release-please version manifest
├── .github/                       # CI workflows
├── scripts/                       # Release & intra-repo dependency tooling
│   ├── sync-intra-deps.sh         # Re-pin okf-go in every consumer to the release version
│   ├── ci-localize-okfgo.sh       # Make an unpublished okf-go pin resolvable in CI
│   ├── verify-release.sh          # Prove every module installs/builds standalone (GOWORK=off)
│   └── dryrun-pin-sync.sh         # Local dry-run of the release pin-sync flow
├── okf-go/                        # Shared Go library (YAML/MD serialization, ignore/metadata helpers)
│   ├── okf.go                     # Core types: Frontmatter, ConceptDoc, helpers
│   ├── okf_test.go                # Unit tests
│   └── okf-SPEC.md               # Full OKF specification document
├── okf-mcp/                       # Generic MCP server — the host that exposes skills (not a skill)
├── skills/                        # Standalone Go-based CLI skills
│   ├── okf-sqlite/                # SQLite connector (CGO-free)
│   ├── okf-graphql/                # GraphQL Type connector
│   ├── okf-mongodb/                # MongoDB Collection connector
│   ├── okf-openapi/                # API Endpoint connector
│   ├── okf-csv/                # CSV File connector
│   ├── okf-mysql/                 # MySQL connector
│   ├── okf-postgresql/            # PostgreSQL connector
│   ├── okf-bigquery/              # GCP BigQuery connector
│   ├── okf-fs/                    # Local filesystem connector
│   ├── okf-git/                   # Git repository connector
│   ├── okf-enrich/                # Enrichment guidance skill (Instructions-only)
│   ├── okf-reader/                # Ingestion guidance skill (Instructions-only)
│   ├── okf-producer-generator/    # Producer-authoring guidance skill (Instructions-only)
│   ├── okf-viz/                   # Bundle visualizer — renders OKF bundles to interactive HTML
│   └── okf-lint/                  # Bundle validator — spec conformance + coverage, CI gate
└── tests/                         # Central integration testing directory
    ├── docker-compose.yml         # MySQL & PostgreSQL containers
    ├── helpers_test.go            # Shared test utilities (getBinaryPath, isPortOpen, etc.)
    ├── db_integration_test.go     # SQLite, MySQL, PostgreSQL integration tests
    ├── fs_integration_test.go     # Filesystem integration tests
    ├── git_integration_test.go    # Git integration tests
    ├── mcp_integration_test.go    # schema-contract checks + okf-mcp discovery
    ├── viz_integration_test.go    # okf-viz render integration tests
    ├── mysql/
    │   └── init_mysql.sql         # Sample MySQL schema with comments
    ├── postgres/
    │   └── init_postgres.sql      # Sample PostgreSQL schema with comments
    └── testdata/                   # Test fixtures & sample data

Read the full file on GitHub · 216 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. 9d ago First seen · 216 lines · 3,959 tokens per session scan B b693e3c66922

Subscribe to this mod's changes

okf-skills AGENTS.md is an instructions file published in the GitHub repository xSAVIKx/okf-skills (33 stars, last pushed 9d ago), licensed Apache-2.0. It adds 3,959 tokens to every session, about $0.0198 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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