Borrowing it
Nothing to install: this file belongs to princeofscale/bloxforge. 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/princeofscale/bloxforge/main/CLAUDE.mdgit clone --depth 1 https://github.com/princeofscale/bloxforgeWrote 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/instructions/princeofscale/bloxforge/claude-md)<a href="https://agentmods.dev/instructions/princeofscale/bloxforge/claude-md"><img src="https://agentmods.dev/badge/instructions/princeofscale/bloxforge/claude-md/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/instructions/princeofscale/bloxforge/claude-md"><img src="https://agentmods.dev/badge/instructions/princeofscale/bloxforge/claude-md.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 | $0.03597 | $0.03597 |
| Opus 5.5 | $0.01439 | $0.01439 |
| Sonnet 5.5 | $0.00719 | $0.00719 |
| Haiku 4.5 | $0.00360 | $0.00360 |
Grade A, and why
bloxforge CLAUDE.md 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BloxForge agent guide
The primary operating guide for AI coding agents working in this repository.
Follow any more specific AGENTS.md found deeper in the tree as well.
If you are an agent using BloxForge to build a Roblox game, you want README.md and docs/tools-reference.md instead.
Project purpose
BloxForge is a local-first Model Context Protocol server plus a Roblox Studio plugin. MCP clients inspect and modify Roblox experiences through a localhost bridge. Preserve local-only operation, user control, and compatibility with existing MCP clients.
Repository map
| Path | Contents |
|---|---|
packages/core/ |
Shared tool definitions, handlers, bridge, builders, Rojo/Rokit/Wally adapters, tests |
packages/robloxstudio-mcp/ |
Main CLI, published as @princeofscale/bloxforge |
packages/robloxstudio-mcp-inspector/ |
Read-focused CLI, published as @princeofscale/bloxforge-inspector |
studio-plugin/ |
TypeScript compiled to the Studio Luau plugin via roblox-ts |
scripts/ |
Build, docs, package, release, and integration utilities |
tests/ |
Repository-level integration and regression coverage |
docs/ |
Maintained user and contributor documentation |
evals/ |
Evaluation fixtures and scenarios |
Never commit build output, tarballs, installed Studio plugins, credentials, or local tool state.
Invariants
Break one of these and the failure is silent, so they are listed before the workflow rules.
- Effects are declared, never inferred.
ToolDefinition.effectsis required. Do not reintroduce name-pattern inference: it once markedexport_rbxm(Studio read + local file write) as reaching the network, and worse, it under-declared any new tool whose name did not match a pattern. - Plans are immutable. Anything that applies a previously previewed change
takes the preview's
planHashand refuses a stale one. A plan hash must cover every input the apply depends on — the operations, the remote identities, and the current content of every local file involved. - Re-read before you write. Every apply path re-checks the file against what the plan recorded, immediately before mutating it. Adding a new mutation path means adding that check; this has been the source of several data-loss bugs.
- A toolchain pin outranks
PATH. Ifrokit.toml/aftman.tomlpins a tool, resolve the absolute shim. Never fall back to a bare command name —execFile('rojo')searchesPATHeven when the resolved metadata sayssource: 'rokit'. - The bridge and plugin protocol are a compatibility boundary. No silent request or response shape changes.
- Fail closed. A damaged state file, an unparsable manifest, or an
unsupported CLI flag stops the operation with an explanation. Never guess,
and never silently downgrade (for example, dropping
--locked). - Secrets stay out of source, logs, fixtures, changelogs, commits, and command output. Never print npm or GitHub tokens.
- Reconcile restores declared state and never invents new state. A step
that installs the exact version a manifest pins, or the packages a lock
already resolved, is a repair. Choosing a version, resolving a new lock,
editing the Rojo tree, or migrating Aftman is a decision: it comes back as a
blocked step naming the
[automation]flag that would permit it. When adding a step toproject-reconcile.ts, decide which side of that line it is on before writing the implementation.
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 · 275 lines · 3,597 tokens per session scan A d57233822a34
bloxforge CLAUDE.md is an instructions file published in the GitHub repository princeofscale/bloxforge (7 stars, last pushed 15d ago), licensed MIT. It adds 3,597 tokens to every session, about $0.0144 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.