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.
npx agentmods add instructions/notnull92/hera-agent-godot/agents-mdgit clone --depth 1 https://github.com/NotNull92/hera-agent-godotWrote 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.
[](https://agentmods.dev/instructions/notnull92/hera-agent-godot/agents-md)<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>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.
| Model | Per session | Once 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 |
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.
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 indocs/releases/or the ROADMAP) whenever it changes. mainis shared: never force-push or rewrite pushed history; rebase local-only work.- The same gates apply regardless of agent:
go build/vet/test+gofmtfor Go; Godot--check-onlyfor GDScript; sync README (EN/KO),docs/COMMANDS.md, anddocs/ROADMAP.mdwhen the surface changes, and regenerate the contract goldens whendocs/CONTRACT.mdbehavior 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-qacorpus). 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.
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.
- 6d ago First seen · 247 lines · 3,908 tokens per session scan A a33b758ed54e
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.
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.
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.
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.
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.
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.
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/).