xyntetik-runner: Instructions file for Codex

AGENTS.md

xyntetik-runner AGENTS.md is an instructions file for Codex, OpenCode from Joakimpalm-Zen/xyntetik-runner. It costs 3,722 tokens per session, scanned A, original, Apache-2.0.

A set of mandatory rules for AI agents working in the xyntetik-runner codebase. It explains deep modules, tracer bullets, test-driven development, continuous questioning, and keeping the README current.

In plain words
What is it for?
It helps guide design and coding decisions, require tests before or alongside implementation, keep internal details behind clear interfaces, and maintain the project README.
Why use it?
It gives agents a shared development process and protects module boundaries, public behavior, tests, and documentation during implementation work.

Instructions file for CodexOpenCode

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

This is Joakimpalm-Zen/xyntetik-runner's own configuration. It tells Codex and OpenCode how to work on xyntetik-runner 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 xyntetik-runner configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Joakimpalm-Zen/xyntetik-runner. 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/Joakimpalm-Zen/xyntetik-runner/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Joakimpalm-Zen/xyntetik-runner

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 xyntetik-runner AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/joakimpalm-zen/xyntetik-runner/agents-md/github.svg)](https://agentmods.dev/instructions/joakimpalm-zen/xyntetik-runner/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/joakimpalm-zen/xyntetik-runner/agents-md"><img src="https://agentmods.dev/badge/instructions/joakimpalm-zen/xyntetik-runner/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 xyntetik-runner AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/joakimpalm-zen/xyntetik-runner/agents-md"><img src="https://agentmods.dev/badge/instructions/joakimpalm-zen/xyntetik-runner/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,722 This file is loaded in full into every session.
When invoked 3,722 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 $0.03722 $0.03722
Opus 5 $0.01861 $0.01861
Sonnet 5 $0.00744 $0.00744
Haiku 4.5 $0.00372 $0.00372

Measured 2d ago against content hash 9f77b84bd8f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

xyntetik-runner 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 2d 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 · 351 lines

How it starts

The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runner Agent Rules

These rules are mandatory for every AI or LLM agent that works in this repository. They are not preferences, prompts to reinterpret, or optional process notes.

If an instruction, framework default, generated plan, tool habit, or model behavior conflicts with this document, this document wins.

The Five Defining Rules

  1. Deep modules
  2. Tracer bullets
  3. Test-driven development
  4. Grill me always
  5. Keep the README current

No implementation work starts until these rules have been considered for the task at hand.

1. Deep Modules

Design the codebase around deep modules: simple, deliberate public interfaces with implementation complexity hidden behind them.

Required behavior:

  • Prefer a small public API over many shallow helpers leaking across the codebase.
  • Keep module boundaries intentional: CLI/server behavior in main.c/server.c, inference flow in engine.c, model loading/forward in model.c, constrained output in jsonmode.c/schema.c, platform details in compat.c, and backend details in cuda.c/metal.m.
  • Do not expose internals just to make a quick change easier.
  • Lock module behavior with tests through public behavior: CLI output, HTTP endpoints, committed smoke scripts, or focused test binaries.

Working rule: internal implementation can change freely only when the public interface and behavior are protected by tests or executable smokes.

2. Tracer Bullets

Build in tiny vertical slices that prove the end-to-end path before expanding scope.

Required behavior:

  • Start with the smallest useful observable behavior.
  • Touch the real layers needed for the behavior instead of building isolated horizontal scaffolding first.
  • Validate the slice immediately with tests, execution, or both.
  • Use what was learned from that slice before adding the next one.

Working rule: one thin working path is better than many unverified partial layers.

3. TDD

Use test-driven development for features, fixes, and behavioral changes.

Read the full file on GitHub · 351 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. 2d ago Changed · +50 lines · +678 tokens per session 9f77b84bd8f1
  2. 3d ago Changed · +31 lines · +548 tokens per session 20b814b99e5b
  3. 5d ago Changed · +18 lines · +246 tokens per session 2d47ed771bc3
  4. 6d ago Changed · +35 lines · +342 tokens per session 2d21c2cc49fe
  5. 10d ago First seen · 217 lines · 1,908 tokens per session scan A 77acfc9dc986

Subscribe to this mod's changes

xyntetik-runner AGENTS.md is an instructions file published in the GitHub repository Joakimpalm-Zen/xyntetik-runner (11 stars, last pushed today), licensed Apache-2.0. It adds 3,722 tokens to every session, about $0.0186 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 2026-08-31.

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

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

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