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 AshExplained/roblox-skills --skill roblox-to-issuesgit clone --depth 1 https://github.com/AshExplained/roblox-skillsWrote 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/ashexplained/roblox-skills/roblox-to-issues)<a href="https://agentmods.dev/skills/ashexplained/roblox-skills/roblox-to-issues"><img src="https://agentmods.dev/badge/skills/ashexplained/roblox-skills/roblox-to-issues/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/ashexplained/roblox-skills/roblox-to-issues"><img src="https://agentmods.dev/badge/skills/ashexplained/roblox-skills/roblox-to-issues.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 | $0.00105 | $0.01256 |
| Opus 5.5 | $0.00042 | $0.00502 |
| Sonnet 5.5 | $0.00021 | $0.00251 |
| Haiku 4.5 | $0.00011 | $0.00126 |
Grade A, and why
roblox-to-issues 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 2mo 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.
Roblox → Issues (Vertical Slices)
Break a plan into small issues that are each buildable and playtestable on their own. This is the antidote to "build the whole game in one go, everything half-broken."
The tracker location and label vocabulary should have been provided to you in CLAUDE.md / docs/agents/. If not, run setup-roblox-skills. Slices publish either as GitHub issues (gh) or as markdown files under roadmap/<feature-slug>/slices/ — whichever the setup configured. In all cases, keep ROADMAP.md as the human-readable index.
What a Roblox vertical slice is
A tracer bullet: the thinnest end-to-end path that a player can actually feel, cutting through every layer it touches — client input, server authority, remotes, DataStore, and UI — not one horizontal layer.
- Right (vertical): "Player taps the ore, server grants 1 coin, HUD shows the new balance, balance survives rejoin." Touches input + remote + server + data + UI. Playable.
- Wrong (horizontal): "Build the entire economy module." / "Build all the UI." Nothing is playable until everything is done — exactly the failure we are avoiding.
Slice rules
- Each slice delivers one narrow but complete player-facing capability.
- Each slice is verifiable in a Studio playtest on its own (this is the acceptance signal).
- Prefer many thin slices over a few thick ones. If a slice can't be playtested in isolation, split it.
- Valuable state (currency, inventory, purchases, rewards, progression) is server-authoritative from the first slice — never a client-trust shortcut you plan to fix later.
- The first slice is the tracer bullet: the smallest thing that proves the core loop end-to-end (one action → one reward → one visible next goal). Build it before anything else.
Slice types
- AFK — can be built and verified without a human decision. Prefer these.
- HITL — needs a human: a design approval, a balance judgment call, a Studio action only the user can take. UI slices are HITL until an approved UI design artifact exists (see
roblox-game-ux); if UI design is missing, create a design-approval slice first and block the UI slice on it.
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.
- 2mo ago First seen · 92 lines · 105 tokens per session scan A dab943703fb8
roblox-to-issues is a skill published in the GitHub repository AshExplained/roblox-skills (50 stars, last pushed 4mo ago), licensed MIT. It adds 105 tokens to every session and 1,256 once invoked, about $0.0004 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.
roblox-to-issues compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| roblox-to-issuesAshExplained/roblox-skills | Skill | 50 | 4mo ago | MIT | A | 105 | Claude Code, Codex |
| game-builderOneWave-AI/claude-skills | Skill | 415 | 18d ago | MIT | A | 0 | Claude Code, Codex |
| gamemaker-gmlMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 76 | Claude Code |
| game-developmentMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 23 | Claude Code |
| pixi-jsMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 24 | Claude Code |
| luaMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 21 | Claude Code |
| gaming-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 51 | Claude Code |