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 skills add striderZA/OpenCodeGameStudios --skill autopilot-playtestgit clone --depth 1 https://github.com/striderZA/OpenCodeGameStudiosWrote 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/skills/striderza/opencodegamestudios/autopilot-playtest)<a href="https://agentmods.dev/skills/striderza/opencodegamestudios/autopilot-playtest"><img src="https://agentmods.dev/badge/skills/striderza/opencodegamestudios/autopilot-playtest/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.
<a href="https://agentmods.dev/skills/striderza/opencodegamestudios/autopilot-playtest"><img src="https://agentmods.dev/badge/skills/striderza/opencodegamestudios/autopilot-playtest.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00070 | $0.01899 |
| Opus 5.5 | $0.00028 | $0.00760 |
| Sonnet 5.5 | $0.00014 | $0.00380 |
| Haiku 4.5 | $0.00007 | $0.00190 |
Grade A, and why
autopilot-playtest 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automated Playtest with Autopilot
Autopilot plays the game open in the Godot editor. You write the harness for this request, run it through Autopilot's MCP tools, and file what play showed.
Autopilot's own instructions (INSTRUCTIONS.md, named by start_run) are the detailed reference. This skill is the framework's wrapper around them.
The result is automated evidence. It is never a human playtest.
Setup (once per machine and project)
Rationale and verified behaviour: docs/framework/autopilot-integration.md.
- Harness. OpenCode 2.2.5, Pi 1.x and omp 18.16.0 are verified. Tool names differ by harness. In this skill, a bare name such as
start_runmeans Autopilot's MCP tool of that name, shown asautopilot_start_runin OpenCode,mcp__autopilot__start_runin Pi andmcp__autopilot_start_runin omp. Other harnesses: stop and say so, and do not edit their config. - Godot 4.7 or later. Autopilot's addon README states this. The addon is tested on 4.7.2, which this framework's Godot reference is pinned to. The addon has no runtime version check, so Godot 4.6 is untested.
- Addon. Install
addons/autopilot/into the game project from Autopilot's download. Enable it in Project Settings > Plugins, then commit theproject.godotchanges it makes (autoloadAutopilotPlaytest, andautopilot/project_id). Do not copy the addon into this repository. - Agent service and Bun. Install Autopilot's agent service, which provides the
autopilotcommand thatopencode.jsonruns. Install Bun, which Autopilot's default harness agent needs. - Keys. Bring your own keys: a TypeSafe decision key and an LLM key, both in Autopilot's
autopilot.env. Do not sign in to Aura. - Sharing. In the dock's Privacy step, turn sharing off. Autopilot shares recordings, screenshots, traces and memories by default.
- Releases. Exclude
addons/autopilot/*from export presets.
Phase 1: Preflight
- Confirm the server is enabled for this session. In OpenCode,
opencode.json→mcp.servers.autopilotmust havedisabledset tofalse. In Pi, theautopilotentry in yourmcp.jsonmust haveenabledset totrueandexposureset todirect. Pi's own MCP view can enable the server, and after editing the file, reconnect the server there or restart Pi. In omp, theautopilotentry in.omp/mcp.jsonmust haveenabledset totrue; restart omp after editing it. If it is off, ask the user whether to enable it for this session, then stop until they answer. If the entry is missing, stop and tell the user to add it from the Autopilot section of/setup-engine. Do not edit config files yourself. - Readiness. The Autopilot tools join your tool list only after the MCP server starts. That took about 5 seconds in testing and can take longer on a cold start. Check that
autopilot_start_run(OpenCode),mcp__autopilot__start_run(Pi) ormcp__autopilot_start_run(omp) is among your tools. If it is not, make one cheap read-only call (for examplereadonAGENTS.md) so the next turn sees the tools, then check again. Make at most 20 such checks. If the tool is still missing, stop and tell the user: "Autopilot's MCP server did not start. Check that theautopilotcommand is on PATH, then runopencode mcp list(OpenCode),pi mcp list(Pi) or/mcp list(omp). Send the request again onceautopilotshows connected." - Confirm the game's project is open in the Godot editor with the Autopilot dock connected. If
start_runsays the agent service isn't running, relay its message and stop. - Keys: never ask the user to paste a key into this chat. If a run asks for a key, tell the user where it goes (see Setup).
- Sharing: confirm the dock's Privacy step is off (see Setup). If the user has not confirmed this, ask before the first run.
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 · 92 lines · 70 tokens per session scan A 31129ba065ec
autopilot-playtest is a skill published in the GitHub repository striderZA/OpenCodeGameStudios (122 stars, last pushed 5d ago), licensed MIT. It adds 70 tokens to every session and 1,899 once invoked, about $0.0003 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 2026-11-05.
autopilot-playtest compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| autopilot-playteststriderZA/OpenCodeGameStudios | Skill | 122 | 5d ago | MIT | A | 70 | Claude Code |
| godot-testing-qadcc-mcp/dcc-mcp-godot | Skill | 5 | 14d ago | MIT | A | 68 | Claude Code |
| professional-game-developerchahat1709/professional-game-developer.skill | Skill | 4 | 2mo ago | MIT | A | 103 | Claude Code |
| design-systemTraftG/opencode-game-studio | Skill | 50 | 7mo ago | MIT | A | 45 | Claude Code, OpenCode |
| setup-engineTraftG/opencode-game-studio | Skill | 50 | 7mo ago | MIT | A | 45 | Claude Code, OpenCode |
| gate-checkTraftG/opencode-game-studio | Skill | 50 | 7mo ago | MIT | A | 29 | Claude Code, OpenCode |
| launch-checklistTraftG/opencode-game-studio | Skill | 50 | 7mo ago | MIT | A | 33 | Claude Code, OpenCode |