Borrowing it
Nothing to install: this file belongs to developerz-ai/open-mmorpg. 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/developerz-ai/open-mmorpg/main/.claude/commands/feature.mdgit clone --depth 1 https://github.com/developerz-ai/open-mmorpgWrote 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/commands/developerz-ai/open-mmorpg/feature)<a href="https://agentmods.dev/commands/developerz-ai/open-mmorpg/feature"><img src="https://agentmods.dev/badge/commands/developerz-ai/open-mmorpg/feature/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/commands/developerz-ai/open-mmorpg/feature"><img src="https://agentmods.dev/badge/commands/developerz-ai/open-mmorpg/feature.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 | $0.00071 | $0.05261 |
| Opus 5.5 | $0.00028 | $0.02104 |
| Sonnet 5.5 | $0.00014 | $0.01052 |
| Haiku 4.5 | $0.00007 | $0.00526 |
Grade A, and why
feature 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 15d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feature
You are a senior engineer on open-mmorpg — an open-core MMORPG engine: Rust server and Bevy client, a Bun/SolidJS operator web portal, original IP, MIT. Read CLAUDE.md and the relevant docs/architecture/ page before designing. The binding decisions — Rust everywhere (except apps/web), server-authoritative always, ownership writes go to YugabyteDB in a transaction, content is data and core is compiled, open formats only, original IP only, horizontal from day 1 — are not up for re-litigation.
Done means merged and verified — nothing less counts. There is no production cluster yet: docker.yml builds images to GHCR on workflow_dispatch only and is deliberately not wired to a deploy, so the arc ends at merged on main with bin/check green and the behaviour actually demonstrated — a replay/golden test for anything touching determinism, a booted stack for anything player- or operator-facing. A green local gate on one crate is not done; an open PR is not done. Report which of those you actually ran rather than which you assume passed.
Request
$ARGUMENTS
The prompt is the context — read the intent. How autonomous to be, how big the scope, which crate or app, whether to confirm before merging: infer it from the words. "Do full work" / "just ship it" → run start to finish, decide everything yourself, merge on green, no check-ins; surface decisions in the PR body instead of asking. A tentative or exploratory ask → clarify what is genuinely ambiguous and let the user review before you merge. Don't make the user configure you. The flow is a map, not a checklist — but always stop for a true blocker: a binding decision you would have to break, a dupe or data-integrity risk on the ownership path, an anti-cheat hole, an IP-provenance question about an asset or a name, or an external dep you cannot satisfy.
Pick the PR mode before you brief anyone. Slice-per-PR (default) — one crate or app per PR, merged one at a time; it maps onto the crate boundaries you are already slicing along. One fat PR is the user's call for a coherent sweep; path-disjointness still governs the build (it is how parallel agents avoid clobbering each other), not the commit, and the PR body carries the finding-by-finding ledger.
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.
- 15d ago First seen · 129 lines · 71 tokens per session scan A fac1e523ab2c
feature is a command published in the GitHub repository developerz-ai/open-mmorpg (12 stars, last pushed 6d ago), licensed MIT. It adds 71 tokens to every session and 5,261 once invoked, about $0.0003 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 2026-10-02.
Other commands, from other repositories
fix-issues
Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.
update-pr-body
Bring the pull request's description in line with the final change. It was written when the draft opened; the base merge and correction rounds since then may have falsified claims in it, and a validation may have passed red it has to disclose. Your product is an accurate description, nothing else.
build-and-compilation
These commands drive the build/compile/test dev loop, plus build configuration: triggering Player builds and reading the resulting BuildReport, switching the active build target, enumerating targets, reading/writing EditorUserBuildSettings, and listing Build Profiles. Several commands are asynchronous: trigger the…
project-settings
Read and change a representative slice of Unity's project-wide settings (Audio, Graphics, Input, Physics, Player, Quality, Tags & Layers, Time). get commands read a group's current values into a ProjectSettingsResponse; set commands mutate them through the shared confirm/dryrun convention, so confirm=true is required…
gameobjects-and-components
Commands for creating GameObjects, querying the scene hierarchy, mutating the core GameObject/Transform surface, and adding/removing components and editing their serialized properties. Scene mutations are wrapped in Unity's Undo system (so a multi-step action reverts as one collapsible step) and are blocked during…
runtime
Commands served by the Player / dev-build server. Many require a Development build running RuntimePipelineManager — see Runtime setup. Commands marked RuntimeOnly are only registered in a player build.