estella-workflow

estella-workflow is a skill for Claude Code, Codex from esengine/estella. It costs 58 tokens per session (1,147 once invoked), scanned A, original, Apache-2.0.

How to get a task done in an Estella game project through the editor's MCP tools - open the project, write the acceptance first, build, verify until it passes. Read this before any other Estella skill and at the start of every Estella task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install with agentmods
npx agentmods add skills/esengine/estella/estella-workflow
About the project

Estella is a 2D and 3D game engine with a TypeScript interface, a C++/WebAssembly core, and a visual editor that also acts as an MCP server. It helps developers create, test, and export games for the web, desktop, mini-game platforms, playable ads, and native mobile devices. Its catalogue add-ons let coding agents operate the editor through the same tool surface used by its interface.

esengine/estella · 1,174 stars · on GitHub · estellaengine.com

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 esengine/estella --skill estella-workflow
Clone the repo
git clone --depth 1 https://github.com/esengine/estella

Made for: Claude Code, Codex.

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 estella-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/esengine/estella/estella-workflow/github.svg)](https://agentmods.dev/skills/esengine/estella/estella-workflow)
Your own site
<a href="https://agentmods.dev/skills/esengine/estella/estella-workflow"><img src="https://agentmods.dev/badge/skills/esengine/estella/estella-workflow/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 estella-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/esengine/estella/estella-workflow"><img src="https://agentmods.dev/badge/skills/esengine/estella/estella-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,147 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 unknown 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 $0.00058 $0.01147
Opus 5.5 $0.00023 $0.00459
Sonnet 5.5 $0.00012 $0.00229
Haiku 4.5 $0.00006 $0.00115

Measured today against content hash 904bca405c25, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

estella-workflow 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 today.

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.

skills/estella-workflow/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working in Estella

Estella is a game engine with an editor. You drive the editor through its MCP tools; the editor holds the project, the open scene and a running game. Everything below is about not losing a task to the four ways agents usually do: working on the wrong world, waiting for a game that is not moving, reporting success without looking, and changes that never reach disk.

The loop

  1. Know the project. get_workspace_session says what is open. No project: list_project_templates, create_project, then open_project (it returns once the first scene is readable). get_scene_tree shows the scene.
  2. Write the acceptance first. Put what "done" means in acceptance/<task>.json with write_project_file:
    { "frames": 120,
      "inputs": [{ "frame": 10, "kind": "key_down", "code": "Space" }],
      "expect": [{ "entity": "Player", "component": "Transform", "field": "position.y", "op": "changed", "says": "the player jumps" }] }
    
    One expectation per thing the task asked for. op is == != > >= < <= ~= (with tolerance), exists, absent, changed, unchanged; changed compares with the value when play began, before any input.
  3. Build with the tools (see the other Estella skills for each kind of work).
  4. Verify: verify { acceptance: "acceptance/<task>.json" }. It checks that the scripts build, that the scene has no empty required field or dead reference, that nothing blocks a build, runs the game with your inputs, checks your expectations, fails on any error logged while it ran, and fails a game view that is one flat colour. Work until pass is true, fixing what each finding's fix says. Then look once with screenshot { crop: "game" }.
  5. Save: save_scene. Scene edits are not on disk until then.

Two worlds

  • The open scene is what is saved: search_entities, get_entity, set_field, apply_scene_ops, add_component.
  • The running game is a copy made when play starts and thrown away when it stops: set_play, step, play_input, find_entities, inspect_entity. A change made in the running game is gone at Stop; a change to the scene does not reach a game already running (stop and play again).
  • The two number their entities differently: the Player is 6 in the scene and some large number in the running game. Every entity argument also takes a name, looked up in the world that tool acts on, so { "entity": "Player" } works in both; a name two entities share is refused with their numbers (in the scene, a path such as "HUD/ScoreText" picks one).

Read the full file on GitHub · 65 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. today First seen · 65 lines · 58 tokens per session scan A 904bca405c25

Subscribe to this mod's changes

estella-workflow is a skill published in the GitHub repository esengine/estella (1,174 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 1,147 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-19.

Related

estella-workflow compared with skills from other repositories

estella-workflow next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
estella-workflowesengine/estellaSkill1.2ktodayApache-2.0A58Claude Code, Codex
chroniclemicrosoft/vscodeSkill196ktodayMITA72Claude Code, Codex
generate-run-commandsmicrosoft/vscodeSkill196ktodayMITA36Claude Code, Codex
automatemicrosoft/vscodeSkill196ktodayMITA40Claude Code
debugging-executionsn8n-io/n8nSkill211ktodaynoneA86Claude Code, Codex
workflow-buildern8n-io/n8nSkill211ktodaynoneA152Claude Code, Codex
suggest-automationsn8n-io/n8nSkill211ktodaynoneA87Claude Code, Codex