godmode AGENTS.md

Contributor guidance for Godmode, a portable collection of reusable instructions for AI coding assistants. It covers how to design, organize, validate, and document skills.

In plain words
What is it for?
Use it when adding or revising skills, arranging reference files, validating skill definitions, or changing the catalogue's public vocabulary.
Why use it?
It helps contributors keep the public skill catalogue focused and makes changes repeatable and testable. It also clarifies which project documents must be read before changing the catalogue.

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

Made for: Codex, OpenCode.

Per session 389 This file is loaded in full into every session.
When invoked 389 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 $0.00389 $0.00389
Opus 5 $0.00195 $0.00195
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 2d ago against content hash 7efe00f307c2, 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 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 · 47 lines

What it actually says

Godmode contributor instructions

Godmode is a portable Agent Skills project. Read docs/architecture.md and docs/research.md before changing the public catalog or its vocabulary.

Working rules

  • Keep the public catalog intentional. A public skill must represent a coherent engineering responsibility or workflow, not a single technique. Familiar names are preferred when they accurately describe a distinct responsibility; combine only when the boundary is genuinely clearer.
  • Use the Agent Skills format: every public skill is a directory containing a SKILL.md with valid YAML frontmatter. Keep the body focused and move optional detail to one-level-deep references/ files.
  • Write behavior from first principles. Do not copy implementation text, datasets, scripts, or proprietary material from reference projects.
  • Keep local research checkouts outside the runtime and package inputs.
  • Prefer standard-library validation and deterministic tests. Do not add a runtime dependency for routing when native skill discovery is sufficient. Domain helpers may be dependency-free scripts when they produce repeatable artifacts or audits.
  • Every workflow must identify what it needs to inspect, what it may change, and what evidence is required before a completion claim.
  • Keep descriptions precise enough to route adjacent tasks without making unrelated skills compete.

Verification

Run the complete local gate before reporting a change as complete:

python3 scripts/validate.py
python3 -m unittest discover -s tests -p 'test_*.py'

If a change affects a plugin manifest, also run the relevant native validator when the client is installed:

claude plugin validate .

Codex compatibility must be checked through its local plugin help and marketplace/plugin validation path when that client exposes one. Do not claim that an agent loaded a skill unless a real session or native validator proves it.

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 · 47 lines · 389 tokens per session scan A 7efe00f307c2

Subscribe to this mod's changes

godmode AGENTS.md is an instructions file published in the GitHub repository thiientv/godmode (93 stars, last pushed 7d ago), licensed MIT. It adds 389 tokens to every session, about $0.0019 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.