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 dcc-mcp/dcc-mcp-godot --skill godot-exportgit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-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/skills/dcc-mcp/dcc-mcp-godot/godot-export)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-godot/godot-export"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-godot/godot-export/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/dcc-mcp/dcc-mcp-godot/godot-export"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-godot/godot-export.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 | $0.00062 | $0.00609 |
| Opus 5.5 | $0.00025 | $0.00244 |
| Sonnet 5.5 | $0.00012 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
godot-export 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 3d 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.
What it actually says
Godot Export
For a packaging, runnable game, standalone, EXE, or playtest delivery request, report readiness in the first response, before authoring or opening a GUI. Read Cross-platform packaging and identify the exact engine version/build, edition, architecture, target OS, named preset, matching template identity/cache, disk needs and download size. State missing inputs immediately. An EXE request is not download permission; preserve existing projects, saves and caches while resolving dependencies through normal consent.
Use these editor-integrated tools after opening the target Godot project. Start
with get_export_info and list_export_presets; do not mutate a preset or
attempt a release export until the requested target and matching template are
known. Paths passed to the tools must remain under res://.
Prefer start_export_job with a stable 32-hex request ID and a fresh dedicated
output directory, then get_export_job. A lost start response is queried with
that same ID, never blindly repeated under a new ID. cancel_export_job reports
actual child cleanup, not assumed termination. Unknown outcomes keep the project
busy. Complete logs and output hashes are file receipts, not truncated bridge
text. Windows cleanup is direct-child-only; do not claim all descendants stopped.
One lazy export manager exclusively owns a registry journal across processes;
other adapters sharing it receive busy without changing records or spawning.
Use the existing explicit private-registry option for isolated adapters; concurrent
multi-Godot exports sharing one registry are not supported in this version.
The legacy export_project remains synchronous and can exceed bridge deadlines.
Read Cross-platform packaging before planning a release build, changing platform presets, or diagnosing a failure that appears only after export. In particular, editor success is not release evidence: launch the exported artifact on the target runtime and verify fonts, resources, storage, input, and startup diagnostics.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · +8 lines · +5 tokens per session 88df50c3833d
- 6d ago Changed · +12 lines 891fcb4a4363
- 1mo ago First seen · 35 lines · 57 tokens per session scan A a461b42c95d3
godot-export is a skill published in the GitHub repository dcc-mcp/dcc-mcp-godot (3 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 609 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 2026-08-31.
Other skills, from other repositories
qa-plan
Generate a QA test plan for a sprint or feature. Reads GDDs and story files, classifies stories by test type (Logic/Integration/Visual/UI), and produces a structured test plan covering automated tests required, manual test cases, smoke test scope, and playtest sign-off requirements. Run before sprint begins or when…
asset-audit
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.
balance-check
Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design. Use when user says 'balance report', 'check game balance', 'run a balance check'.
code-review
Performs an architectural and quality code review on a specified file or set of files. Checks for coding standard compliance, architectural pattern adherence, SOLID principles, testability, and performance concerns.
hybrid-prototype
Fast-lane prototype skill for the hybrid workflow. Builds a playable prototype in 2-3 days with minimal process overhead. Designed for discovery phase.
milestone-review
Generates a comprehensive milestone progress review including feature completeness, quality metrics, risk assessment, and go/no-go recommendation. Use at milestone checkpoints or when evaluating readiness for a milestone deadline.