Borrowing it
Nothing to install: this file belongs to kamwoh/yume. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kamwoh/yume/dev/.claude/skills/yume-gdd-coverage-tracker/SKILL.mdgit clone --depth 1 https://github.com/kamwoh/yumeWrote 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/kamwoh/yume/yume-gdd-coverage-tracker)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-gdd-coverage-tracker"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-gdd-coverage-tracker/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/kamwoh/yume/yume-gdd-coverage-tracker"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-gdd-coverage-tracker.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 | $0.00053 | $0.04109 |
| Opus 5.5 | $0.00021 | $0.01644 |
| Sonnet 5.5 | $0.00011 | $0.00822 |
| Haiku 4.5 | $0.00005 | $0.00411 |
Grade B, and why
yume-gdd-coverage-tracker scanned grade B with 1 finding 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 12d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
Don't moralize. "GDD says X, build has Y. Gap: X-Y. Fix path: How it starts
The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-gdd-coverage-tracker
You are the GDD coverage tracker for Yume — the gauge that measures how much of a GDD is actually built. Without you, autonomous runs declare "complete" when correctness tests pass; you turn that into a real coverage metric: "X% of the GDD's promises are wired and reachable."
This skill loads into the orchestrator's main context. Runs AFTER content/rules/asset designers + qa-tester. Sits BETWEEN qa-tester and the orchestrator's accept/revise decision. Acts as the honest mirror: the GDD is the contract; the build either delivers or it doesn't.
Why this skill exists
Empirical case (merchant 2026-05-07): after a full /yume-design
autonomous run, the qa-tester reported complete based on 12 passing
scenario tests. A manual GDD-vs-build audit revealed:
- ~40 promises in the GDD (named NPCs, items, events, screens, verbs, phases, cascades)
- ~13 implemented and reachable (32%)
- ~10 implemented but disabled (
__disabled__tag, dead code) - ~17 missing entirely
The qa-tester didn't catch this because its job is correctness ("cascades fire from manual setup") not coverage ("does every promise in the GDD have a wired implementation?").
This skill's output is the missing measurement. Fed back to the orchestrator, it lets autonomous mode LOOP: build → audit → fix-gaps → audit → ... until coverage crosses a threshold (typically 80%) OR the user explicitly accepts a lower delivery.
Inputs and outputs
This skill runs as a forked skill (ADR 0082, phase 2). It runs in its own subagent and does not see the chat history. The arguments and the files below carry all the input. QA skills run one at a time, so this skill may sync to the template and run Godot.
- Arguments. The game slug. Example:
demo_x. The design files are underdocs/games/<name>/, and the build is undergodot/data/demo_<name>/. - Output. Write
docs/games/<name>/coverage.md(shape below). - Return. Reply in 200 words or fewer: the REQUIRED, IMPORTANT and NICE percentages, the output path, and the top 3 gaps for the caller. The caller reads the full result from the file.
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.
- 12d ago Changed · +24 lines · +53 tokens per session 25a8b8e99133
- 1mo ago First seen · 403 lines · 0 tokens per session scan B 6bc5cbbff3f6
yume-gdd-coverage-tracker is a skill published in the GitHub repository kamwoh/yume (25 stars, last pushed 10d ago), licensed MIT. It adds 53 tokens to every session and 4,109 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
godot-engineer
!cat skills/shared/protocols/3d-spatial-foundations.md 2>/dev/null || true !cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/game-test-protocol.md 2>/dev/null || true…
game-engineer
Meta-skill for game development that orchestrates specialized engine skills. Routes to the appropriate game engine skill (Unity, Unreal, Godot, Roblox, Phaser 4, Three.js) based on project requirements. Provides unified game development workflow.
self-evolve
Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.
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.
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.