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 agentmods add instructions/princeofscale/bloxforge/claude-mdgit clone --depth 1 https://github.com/princeofscale/bloxforgeWhat 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 | $0.03597 | $0.03597 |
| Opus 5 | $0.01799 | $0.01799 |
| Sonnet 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 3d 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.
- 3d 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 (5 stars, last pushed 6d ago), licensed MIT. It adds 3,597 tokens to every session, about $0.0180 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 instructions, from other repositories
mcp-unity AGENTS.md
Instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
fennara-godot-ai AGENTS.md
Instructions for fennaraOfficial/fennara-godot-ai, covering agent instructions, core rules, source of truth, generated and packaged files and documentation updates.
roblox-brain AGENTS.md
AGENTS.md instructions for TabooHarmony/roblox-brain, covering agents.md: guide for ai agents and contributors, what this repo is, architecture: progressive disclosure, skill file structure and skill title.
godot-mcp-bridge CLAUDE.md
Instructions for TomasLucasUTN/godot-mcp-bridge, covering godot-mcp-bridge — project guide, adding or changing a tool, dev / test loop, tests and gotchas.
godot-mcp-enhanced CLAUDE.md
Claude Code instructions for wgt19861219/godot-mcp-enhanced, covering godot mcp enhanced 项目配置, mcp 工具验证规则, 发版门禁, mcp 子系统速查（详细指南见 .claude/rules/godot-mcp-.md） and src 目录分组规则.
bastion AGENTS.md
Instructions for JoakimCarlsson/bastion, covering agents.md — bastion contributor and agent contract, project summary, hard rules — verification (non-negotiable), smoke example and or: docker compose up --build.