live-editor

live-editor is a skill for Claude Code from NotNull92/hera-agent-godot. It costs 66 tokens per session (999 once invoked), scanned A, original, MIT.

A guide for inspecting and changing a running Godot game or editor through the Hera command-line tool. Godot is a game engine, and Hera reads the live scene, nodes, interface, signals, and gameplay state.

In plain words
What is it for?
Use it to inspect scenes and interface elements, edit nodes and properties, connect signals, run scenes, interact with the game, and verify gameplay or UI behavior.
Why use it?
It prevents relying on outdated project files or guesses when checking or changing what is currently open or running.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the hera-godot plugin — 2 skills shipped together

Good fit Use it to inspect scenes and interface elements, edit nodes and properties, connect signals, run scenes, interact with the game, and verify gameplay or UI behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/notnull92/hera-agent-godot/live-editor
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.

Any agent
npx skills add NotNull92/hera-agent-godot --skill live-editor
Clone the repo
git clone --depth 1 https://github.com/NotNull92/hera-agent-godot

Made for: Claude Code.

Or install hera-godot, the plugin that ships this one along with the rest of its 2 skills.

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 live-editor

README.md
[![agentmods](https://agentmods.dev/badge/skills/notnull92/hera-agent-godot/live-editor/github.svg)](https://agentmods.dev/skills/notnull92/hera-agent-godot/live-editor)
Your own site
<a href="https://agentmods.dev/skills/notnull92/hera-agent-godot/live-editor"><img src="https://agentmods.dev/badge/skills/notnull92/hera-agent-godot/live-editor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for live-editor

Your own site · 80×15
<a href="https://agentmods.dev/skills/notnull92/hera-agent-godot/live-editor"><img src="https://agentmods.dev/badge/skills/notnull92/hera-agent-godot/live-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 999 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00066 $0.00999
Opus 5 $0.00033 $0.00500
Sonnet 5 $0.00013 $0.00200
Haiku 4.5 $0.00007 $0.00100

Measured yesterday against content hash af8d4324639d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

live-editor 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 yesterday.

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.

integrations/claude-code/hera-godot/skills/live-editor/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hera live Godot workflow

Use Hera only with a running Godot editor that has the Hera Agent Godot addon enabled (verified on Godot 4.2–4.7; 4.7 recommended). CLI output is the source of truth for live editor and runtime state.

Start with the live editor

  1. Run hera status. If no live editor is found, ask the user to enable the addon under Project Settings → Plugins; do not infer editor state from files.
  2. If multiple editors are found, run hera instances. Pass hera --instance <pid> for any mutation.
  3. Before UI work, run hera guidance ui and follow its returned mode.

Editor and game PIDs are separate. Use global --instance <editor-pid> for the editor, then game --pid <game-pid> ... to select a fresh entry from game instances, including externally launched games. Keep the game PID on QA commands and scenarios. Never fall back to a different runtime when it expires. --instance/--pid do not isolate user://; if shared_user_data is set, split user data directories before parallel QA. Runtime screenshot sizes are the live viewport; do not assume the project resolution or upscale. If hera instances shows stale, the editor process may still be running with an expired heartbeat — that is not the same as no editor.

Keep reads small and writes safe

  • Default output is compact. Prefer hera --ids scene tree, selected node get --prop/--props, scoped game ui tree, and game qa discover before full dumps.
  • Use node add/set/remove and signal connect/disconnect for normal editor changes; Godot records those as undoable steps. Prefer them to eval, whose expression can have side effects and is not undoable.
  • Scene, resource, script, import, and project-setting commands persist to disk. game node set/call, game click, and game input affect only the running game and disappear when it stops.
  • Keep one editor per project. After direct .tscn edits, stop the game, hera scene reload, then save through the editor.
  • The Hera runtime autoload is excluded from exports and restored afterward; do not persist a separate production autoload for the inspector.

Read the full file on GitHub · 77 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. yesterday Changed · +29 lines af8d4324639d
  2. 9d ago First seen · 48 lines · 66 tokens per session scan A a29c9a5ade18

Subscribe to this mod's changes

live-editor is a skill published in the GitHub repository NotNull92/hera-agent-godot (11 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 999 once invoked, about $0.0003 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.