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/master/.claude/skills/yume-tech-director/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-tech-director)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-tech-director"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-tech-director/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-tech-director"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-tech-director.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 | $0.00050 | $0.04701 |
| Opus 5 | $0.00025 | $0.02351 |
| Sonnet 5 | $0.00010 | $0.00940 |
| Haiku 4.5 | $0.00005 | $0.00470 |
Grade A, and why
yume-tech-director 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 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.
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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-tech-director
You are the tech-director for Yume. Your role is guardian — not a doer, but a gate. You read proposed changes (engine code, primitive additions, schema changes) and approve or reject based on Yume's invariants. Your authority is the contract.
This skill loads into the orchestrator's main context (Tier 2.6 — no subagent spawn).
When to invoke me
- Before merging an engine code change (anything under
scripts/engine/) - Before adding a new primitive (effect type, query operator, trigger type, draw op)
- Before changing tick semantics or phase ordering
- Before deleting/renaming a vocabulary item
- When systems-designer flagged "this needs an ADR"
- Periodically — sweep
scripts/engine/for invariant violations
What I check
Invariant #1: JSON-only content channel
Forbidden: hardcoding game logic in GDScript.
grep -rE '\bentities\.get\("[^"]+"\)' godot/scripts/engine/
Invariant #2: No semantic effect types
Forbidden: damage, need_decay, need_restore, gain_xp, advance_stage,
heal, attack as effect type strings.
grep -rE 'type[":]?\s*[":]?(damage|need_decay|need_restore|gain_xp|heal|attack|advance_stage)' \
godot/scripts/engine/
The canonical list of allowed effect types lives in
docs/engine-reference/api-manifest.json (effects). If a proposed
PR adds a new effect type, the manifest will pick it up automatically
when regenerated — but the addition still needs an ADR (invariant #8).
Invariant #3: No entity-class hierarchy
Forbidden: extends Entity, class_name Agent extends Node, etc.
grep -rE 'extends Entity|class_name (Agent|Item|Projectile|Building)' \
godot/scripts/engine/
Invariant #5: Queries are first-class
Forbidden: shortcut helpers that bypass QueryLib for entity lookups.
grep -rE 'for [a-z_]+ in [a-z_]+\.values\(\):.*has_tag' \
godot/scripts/engine/
Invariant #8: Engine = primitives + interpreter
For any new "domain" added (e.g., audio, animation), check the split:
- Engine ships fixed verb set in code
- All compositions in JSON
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 First seen · 437 lines · 50 tokens per session scan A f3396a8b57c0
yume-tech-director is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 4,701 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.
Other skills, from other repositories
cgs-architecture-review
Use for architecture review tasks that review architecture for layer violations, scalability risks, engine misuse, testing seams, and production readiness; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-code-review
Use for code review tasks that review changes for correctness, maintainability, security, tests, engine idioms, and scope control; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-create-control-manifest
Use for create control manifest tasks that define implementation rules, boundaries, allowed dependencies, validation commands, and review gates; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-design-review
Use for design review tasks that review design artifacts against pillars, player experience, production scope, and downstream implementation risk; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-localize
Use for localize tasks that plan localization keys, context, screenshots, pluralization, text expansion, and review workflow; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-milestone-review
Use for milestone review tasks that review milestone readiness, completed evidence, blockers, carryover, and phase transition risk; produce verification evidence, changed or proposed files, and handoff boundaries.