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-code-maintenance-refactorgit 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-code-maintenance-refactor)<a href="https://agentmods.dev/skills/ashexplained/roblox-skills/roblox-code-maintenance-refactor"><img src="https://agentmods.dev/badge/skills/ashexplained/roblox-skills/roblox-code-maintenance-refactor.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.00526 |
| Opus 5 | $0.00024 | $0.00263 |
| Sonnet 5 | $0.00010 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
roblox-code-maintenance-refactor 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 8d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roblox Code Maintenance Refactor
Goal
Improve code health without changing player-facing behavior accidentally.
Refactor Rules
- Read before editing.
- Keep changes scoped.
- Preserve remote contracts unless intentionally migrating.
- Avoid mixing behavior changes with cleanup.
- Playtest after meaningful refactors.
- Check console output.
Targets
- Duplicated constants and reward formulas.
- Large scripts with mixed responsibilities.
- Client/server boundary confusion.
- Dead remotes, stale UI paths, unused modules.
- Repeated event connection patterns.
- Unclear names around valuable state.
- Magic numbers that should be balance tables.
Finding Deepening Opportunities
Beyond obvious cleanup, hunt for shallow modules to deepen — where the interface is nearly as complex as the implementation, so callers carry complexity that should be hidden.
- Where does understanding one concept require bouncing between many tiny scripts?
- Where were pure helpers extracted only for tidiness, but the real bugs live in how they're called (no locality)?
- Where do client and server share a responsibility that leaks across the remote boundary?
Apply the deletion test to anything you suspect is shallow: if deleting it just moves complexity around, inline it; if deleting it would scatter the same complexity across many call sites, keep it and give it a small, stable interface named from the game's vocabulary. Present each opportunity as: files involved · the friction today · the proposed change · the benefit (locality + testability). Don't propose new indirection for a single implementation. See roblox-luau-architecture for the deep-module model.
MCP Workflow
- Use
script_grepto find duplication, old names, or call sites. - Read all affected scripts with
script_read. - Make small edits with
multi_edit. - Use
start_stop_playto verify the relevant loop. - Check
get_console_output.
Output
Return:
- Refactor goal.
- Behavior preserved.
- Scripts changed.
- Verification performed.
- Follow-up debt items.
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.
- 8d ago First seen · 63 lines · 49 tokens per session scan A 029e51575487
roblox-code-maintenance-refactor is a skill published in the GitHub repository AshExplained/roblox-skills (6 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 526 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
game-code-review
Invoke when the user wants a game-specific code review, architecture check, or technical analysis of game code. Covers frame independence, hot path performance, state machine integrity, and resource lifecycle. Triggers on: "code review", "review my code", "check architecture", "game code quality". Do NOT invoke for…
refactor
Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
work-with-pr
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.