hera-agent-godot AGENTS.md

hera-agent-godot AGENTS.md is an instructions file for Codex, OpenCode from NotNull92/hera-agent-godot. It costs 3,908 tokens per session, scanned A, original, MIT.

A project instruction file for developing and using hera, a command-line tool that inspects and controls a live Godot 4 game editor. It also documents rules for agents co-developing the tool.

In plain words
What is it for?
Use it when working on the hera tool or controlling a Godot project with it. It covers editor checks, repository collaboration, commits, documentation, and release-related records.
Why use it?
It helps agents check the actual Godot editor instead of guessing about scenes or whether changes worked.

Instructions file for CodexOpenCode

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

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/notnull92/hera-agent-godot/agents-md
Clone the repo
git clone --depth 1 https://github.com/NotNull92/hera-agent-godot

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 hera-agent-godot AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/notnull92/hera-agent-godot/agents-md.svg)](https://agentmods.dev/instructions/notnull92/hera-agent-godot/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/notnull92/hera-agent-godot/agents-md"><img src="https://agentmods.dev/badge/instructions/notnull92/hera-agent-godot/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,908 This file is loaded in full into every session.
When invoked 3,908 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 5.1 $0.03908 $0.03908
Opus 5 $0.01954 $0.01954
Sonnet 5 $0.00782 $0.00782
Haiku 4.5 $0.00391 $0.00391

Measured 6d ago against content hash a33b758ed54e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hera-agent-godot 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 6d 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 · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working with hera-agent-godot (for AI agents)

hera (repo: hera-agent-godot) is a low-token CLI that lets you inspect and control a live Godot 4.x editor. Use it to act on the real editor and check the result — don't guess scene structure or whether a change worked from memory. The binary installs as hera; hera-agent-godot is a transitional alias for the same CLI.

Co-developing this repo (Claude Code × Codex)

Claude Code and Codex collaborate on developing hera-agent-godot itself (the Go CLI, the GDScript addon, docs, and distribution) — this section is about building the tool, not driving the editor with it. Rules for both agents:

  • The other agent reconstructs context only from the repo: git history and docs. Make small commits with descriptive English messages; never leave meaningful state only in chat.
  • State that lives outside this repo — Godot Asset Store submissions and the Homebrew tap repo (NotNull92/homebrew-hera) — must be recorded under docs/ (release notes in docs/releases/ or the ROADMAP) whenever it changes.
  • main is shared: never force-push or rewrite pushed history; rebase local-only work.
  • The same gates apply regardless of agent: go build/vet/test + gofmt for Go; Godot --check-only for GDScript; sync README (EN/KO), docs/COMMANDS.md, and docs/ROADMAP.md when the surface changes, and regenerate the contract goldens when docs/CONTRACT.md behavior changes.
  • Outward-facing actions (store uploads, PRs to third-party repos, version bumps/releases) need the user's explicit go-ahead; Asset Store form submission is done by the user personally.
  • Machine-specific facts (Godot binary path, isolated-smoke pattern, toolchain limits, external-form gotchas) live in docs/DEV_MACHINE.md — read it before local Godot smokes, third-party PRs, or publishes, and update it there instead of re-discovering.
  • Ported capabilities must be fully naturalized. When an idea, architecture, or workflow is adapted from an outside tool, what ships is a Hera-native capability: named for the Godot/Hera construct it operates on, and justified from engine behaviour rather than from "the other tool does it this way". Leave no external tool name, no "ported from X" framing, no side-by-side comparison tables, and no borrowed taxonomy labels anywhere in the repo — docs, skills, and code alike. Re-derive each rule from the Godot fact that forces it; if a rule cannot be justified that way, it does not belong. Attribution cuts the other way for copied material: anything actually vendored or licensed keeps its upstream provenance and licence, and published standards stay cited (as WCAG is in the ui-theme-qa corpus). Never strip a credit while keeping copied expression — rewrite the expression genuinely instead. Prefer deriving values from Godot's own defaults over vendoring someone else's data, so the question does not arise.

Read the full file on GitHub · 247 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. 6d ago First seen · 247 lines · 3,908 tokens per session scan A a33b758ed54e

Subscribe to this mod's changes

hera-agent-godot AGENTS.md is an instructions file published in the GitHub repository NotNull92/hera-agent-godot (11 stars, last pushed 1mo ago), licensed MIT. It adds 3,908 tokens to every session, about $0.0195 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.

Related

Other instructions, from other repositories

unity-code-style-guide AGENTS.md

Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.

krogh-jacobsen/unity-code-style-guide · 4,528 tokens

nes-php-glfw copilot-instructions.md

Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.

oliverearl/nes-php-glfw · 2,719 tokens

game-and-watch-retro-go-sd CLAUDE.md

Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.

sylverb/game-and-watch-retro-go-sd · 2,946 tokens

base-building-trap-defense-design-agent-skill CLAUDE.md

Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.

dungnotnull/base-building-trap-defense-design-agent-skill · 1,910 tokens

trident-mcp AGENTS.md

Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.

mordor-forge/trident-mcp · 1,465 tokens

unreal-mcp-additional-tools CLAUDE.md

Claude Code instructions for nodormu/unreal-mcp-additional-tools, covering claude.md, what this is, commands, architecture and transports (src/transports/).

nodormu/unreal-mcp-additional-tools · 1,727 tokens