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 CodePhobiia/claude-roblox-game-studio --skill datastore-reviewgit clone --depth 1 https://github.com/CodePhobiia/claude-roblox-game-studioWrote 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/codephobiia/claude-roblox-game-studio/datastore-review)<a href="https://agentmods.dev/skills/codephobiia/claude-roblox-game-studio/datastore-review"><img src="https://agentmods.dev/badge/skills/codephobiia/claude-roblox-game-studio/datastore-review/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/codephobiia/claude-roblox-game-studio/datastore-review"><img src="https://agentmods.dev/badge/skills/codephobiia/claude-roblox-game-studio/datastore-review.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 | $0.00043 | $0.00573 |
| Opus 5.5 | $0.00017 | $0.00229 |
| Sonnet 5.5 | $0.00009 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
datastore-review 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/datastore-review — DataStore Audit
Delegate to: datastore-architect
Steps:
- Search for all DataStore usage:
grep -rn "DataStoreService" src/ - Search for all MemoryStore usage:
grep -rn "MemoryStoreService" src/ - Search for all BindToClose handlers:
grep -rn "BindToClose" src/ - Search for PlayerAdded / PlayerRemoving:
grep -rn "PlayerAdded\|PlayerRemoving" src/
Check each DataStore operation for:
Critical (must fix):
- All GetAsync/SetAsync/UpdateAsync wrapped in pcall
- Session locking implemented (acquire lock on join, release on leave)
- BindToClose handler saves all player data with timeout
- Player data keyed by UserId (not Name)
- Schema includes version number
- No synchronous DataStore calls in PlayerAdded without yielding protection
Important (should fix):
- Auto-save interval implemented (recommended: every 5 minutes)
- Save debouncing with dirty flag
- Retry logic for failed operations (with exponential backoff)
- Data migration functions for schema version upgrades
- OrderedDataStore used appropriately (leaderboards, rankings)
- Budget monitoring (not exceeding request limits)
Nice to have:
- Data backup system (periodic full save to backup key)
- Analytics on save failures
- Admin tools for data inspection/correction
Output:
Generate a report with findings organized by severity:
# DataStore Review
## Scope
Files analyzed: X
DataStore references found: Y
MemoryStore references found: Z
## Critical Findings
1. **[filepath:line]**: [issue]
- Impact: [data loss / duplication / exploit]
- Fix: [specific code change]
## Important Findings
...
## Anti-Patterns Detected
...
## Recommended Architecture
[If no DataStore code exists yet, suggest the recommended architecture pattern:]
- ServerStorage/PlayerData/PlayerDataService.lua (main API)
- ServerStorage/PlayerData/SessionLock.lua (lock mechanism)
- ServerStorage/PlayerData/Schema.lua (current schema + migrations)
- ServerStorage/PlayerData/Serializer.lua (compress/decompress)
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.
- 1mo ago First seen · 70 lines · 43 tokens per session scan A fd756119c03a
datastore-review is a skill published in the GitHub repository CodePhobiia/claude-roblox-game-studio (15 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 573 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…