godpowers AGENTS.md

An AI-assisted development system that guides projects from an initial idea through production hardening. It is organized into skills, specialists, workflows, routing rules, templates, and validation tools.

In plain words
What is it for?
Use it for project initialization, requirements planning, implementation workflows, validation, and production-hardening tasks.
Why use it?
It provides a defined path for turning an idea into a tested and more production-ready project. Separate stages and reusable templates help structure the work.

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

Made for: Codex, OpenCode.

Per session 1,469 This file is loaded in full into every session.
When invoked 1,469 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 $0.01469 $0.01469
Opus 5 $0.00734 $0.00734
Sonnet 5 $0.00294 $0.00294
Haiku 4.5 $0.00147 $0.00147

Measured 2d ago against content hash 62e352914207, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

godpowers 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 · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Godpowers - Agent Brief

This is the Godpowers repository: an AI-powered development system that takes projects from raw idea to hardened production.

Reading Order

  1. README.md - what this is, how to use it
  2. SKILL.md - the core skill (the brain)
  3. skills/god-mode.md - the autonomous orchestrator
  4. skills/god-init.md - project initialization
  5. skills/god-prd.md through skills/god-harden.md - individual tier skills

Architecture

  • SKILL.md is the main entry point, loaded by AI coding tools
  • skills/ contains individual command skills (one per file)
  • agents/ contains Pillars 1.1 project context only
  • specialists/ contains source contracts installed into each supported host agent registry
  • routing/ contains command routing metadata and intent recipes
  • workflows/ contains executable workflow YAML
  • references/ contains per-tier reference material (antipatterns, examples)
  • bin/ contains the CLI installer (npx godpowers)
  • lib/ contains executable runtime helpers, sync checks, dogfood, dashboard, and release logic
  • scripts/ contains validation and testing scripts
  • templates/ contains artifact templates
  • fixtures/dogfood/ contains messy-repo release dogfood scenarios

Conventions

  • Every skill file has YAML frontmatter with name, description, and trigger phrases
  • Every tier skill documents its gate check (upstream dependency)
  • Every tier skill documents its have-nots (failure modes)
  • Artifacts are written to .godpowers/<tier>/ paths
  • State is tracked in .godpowers/PROGRESS.mdx
  • Dashboard state is computed by lib/dashboard.js
  • Repo docs, repo surface, route quality, recipe coverage, release surface, host capability, and dogfood checks are executable release gates
  • Disk state is authoritative; conversation memory is not

Quality Rules

  • No em dashes or en dashes (use commas, colons, semicolons, or parentheses)
  • No emojis (use +, -, x, ! for status indicators)
  • Every sentence in generated artifacts must be labeled: DECISION, HYPOTHESIS, or OPEN QUESTION
  • Every claim must fail the substitution test (swap in a competitor, sentence must break)

Read the full file on GitHub · 134 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 First seen · 134 lines · 1,469 tokens per session scan A 62e352914207

Subscribe to this mod's changes

godpowers AGENTS.md is an instructions file published in the GitHub repository hannsxpeter/godpowers (5 stars, last pushed 13d ago), licensed MIT. It adds 1,469 tokens to every session, about $0.0073 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.