godmode AGENTS.md

godmode AGENTS.md is an instructions file for Codex, OpenCode from arbazkhan971/godmode. It costs 6,480 tokens per session, scanned A, original, MIT.

Instructions for Godmode, a skill plugin that organizes AI coding work into a cycle of planning, implementation, measurement, and release. It promotes test-driven development, or writing tests before code, along with evidence-based checks and small Git commits.

In plain words
What is it for?
Use it to plan changes, write tests first, iterate using measurements, run release checks, record experiments in Git, and review or roll back changes that do not improve the project.
Why use it?
It gives coding agents a repeatable way to verify changes instead of relying on an untested impression that code is correct. The workflow makes experiments easier to review, keep, or undo.

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/arbazkhan971/godmode/agents-md
Clone the repo
git clone --depth 1 https://github.com/arbazkhan971/godmode

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 godmode AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arbazkhan971/godmode/agents-md.svg)](https://agentmods.dev/instructions/arbazkhan971/godmode/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/arbazkhan971/godmode/agents-md"><img src="https://agentmods.dev/badge/instructions/arbazkhan971/godmode/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,480 This file is loaded in full into every session.
When invoked 6,480 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 $0.06480 $0.06480
Opus 5 $0.03240 $0.03240
Sonnet 5 $0.01296 $0.01296
Haiku 4.5 $0.00648 $0.00648

Measured 4d ago against content hash b43e8d121762, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

godmode 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 4d 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 · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Godmode for AI Coding Agents

Godmode is a skill plugin with 135 specialized skills and 7 subagents that turn AI coding agents into disciplined engineers. Every change is measured, every bad change is reverted, and every experiment is committed.

Core Workflow: The Godmode Loop

THINK  -->  BUILD  -->  OPTIMIZE  -->  SHIP
  1. THINK — Design first. Explore options, write a spec, pick an approach.
  2. BUILD — TDD: write tests first, implement second, review third.
  3. OPTIMIZE — Autonomous iteration loop: measure, hypothesize, modify, verify. Keep what improves, revert what doesn't.
  4. SHIP — Preflight checks (tests, lint, security, types), deploy, monitor, verify.

Key Principles

  • Mechanical verification over vibes. Every claim must be backed by evidence: test output, benchmark numbers, or tool results. Never say "looks good" — prove it.
  • Git-as-memory. Every experiment gets its own commit. Successful changes are kept. Failed changes are reverted. The git log is the audit trail.
  • Atomic changes. One logical change per commit. Small, reviewable, reversible.
  • Automatic rollback. If a change makes things worse (tests fail, performance degrades, errors increase), revert it immediately. No exceptions.

Authoring Discipline

The execution-discipline principles above govern how changes are verified and kept. A complementary authoring-discipline layer governs what gets written in the first place — read skills/principles/SKILL.md before the first Edit on any task that changes behavior.

  • Think Before Coding. State assumptions in one line. If multiple interpretations exist, present them and emit NEEDS_CONTEXT — do NOT pick silently.
  • Simplicity First. Run the pre-MODIFY checklist: inline single-use helpers, delete impossible-case error handlers, reject unrequested configurability. Catch complexity before it is written.
  • Surgical Changes. Every semantically changed line must trace directly to the user's request. Adjacent-code "improvements," formatting churn, and deletions of pre-existing dead code are scope_drift — discard.
  • Goal-Driven Execution. Replace subjective criteria ("works well," "looks good," "is faster") with a shell command that exits zero.

Read the full file on GitHub · 478 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. 4d ago First seen · 478 lines · 6,480 tokens per session scan A b43e8d121762

Subscribe to this mod's changes

godmode AGENTS.md is an instructions file published in the GitHub repository arbazkhan971/godmode (26 stars, last pushed 7d ago), licensed MIT. It adds 6,480 tokens to every session, about $0.0324 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.