toolchain

A code map for the toolchain area, covering project tools, dependency files, manifests, and command execution.

In plain words
What is it for?
Use it to explore or modify support for Wally and Rokit, TOML files, tool resolution, dependency reconciliation, and related checks.
Why use it?
It shows where tool installation, safe paths, project checks, and tool configuration are implemented.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/princeofscale/bloxforge/toolchain
Any agent
npx skills add princeofscale/bloxforge --skill toolchain
Clone the repo
git clone --depth 1 https://github.com/princeofscale/bloxforge

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,282 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.01282
Opus 5 $0.00011 $0.00641
Sonnet 5 $0.00004 $0.00256
Haiku 4.5 $0.00002 $0.00128

Measured 2d ago against content hash a3a1a17c9c67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

toolchain 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 2d 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.

.claude/skills/generated/toolchain/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Toolchain

110 symbols | 10 files | Cohesion: 78%

When to Use

  • Working with code in packages/
  • Understanding how hasCommand, run, clearRojoCommandCache work
  • Modifying toolchain-related functionality

Key Files

File Symbols
packages/core/src/toolchain/wally-tools.ts requireSafeArgument, load, search, supportsLocked, state (+15)
packages/core/src/quality-tools.ts within, allowedProjectRoot, safeExistingPath, safeOutputPath, commandFailure (+13)
packages/core/src/toolchain/project-reconcile.ts ProjectReconciler, constructor, errorText, noWally, inspect (+13)
packages/core/src/toolchain/toml.ts emptyTable, hasOwn, Reader, peek, startsWith (+12)
packages/core/src/toolchain/rokit-tools.ts requireSafeTool, requireSafeSpec, install, addTool, update (+11)
packages/core/src/toolchain/resolver.ts clearToolCommandCache, toolchainRoot, shimPath, findToolchainManifest, startDirectory (+5)
packages/core/src/toolchain/manifest.ts fileHash, planHashOf, planHashMismatch, findManifest, readTomlFile (+2)
packages/core/src/tools/index.ts RobloxStudioTools, getDependencyGraph
packages/core/src/rojo/command-runner.ts clearRojoCommandCache
packages/core/src/tools/setup-registry.ts get_dependency_graph

Entry Points

Start here when exploring this area:

  • hasCommand (Function) — packages/core/src/quality-tools.ts:87
  • run (Function) — packages/core/src/quality-tools.ts:134
  • clearRojoCommandCache (Function) — packages/core/src/rojo/command-runner.ts:42
  • fileHash (Function) — packages/core/src/toolchain/manifest.ts:49
  • planHashOf (Function) — packages/core/src/toolchain/manifest.ts:68

Key Symbols

Symbol Type File Line
ProjectReconciler Class packages/core/src/toolchain/project-reconcile.ts 240
RokitTools Class packages/core/src/toolchain/rokit-tools.ts 144
WallyTools Class packages/core/src/toolchain/wally-tools.ts 153
RobloxStudioTools Class packages/core/src/tools/index.ts 260
hasCommand Function packages/core/src/quality-tools.ts 87
run Function packages/core/src/quality-tools.ts 134
clearRojoCommandCache Function packages/core/src/rojo/command-runner.ts 42
fileHash Function packages/core/src/toolchain/manifest.ts 49
planHashOf Function packages/core/src/toolchain/manifest.ts 68
planHashMismatch Function packages/core/src/toolchain/manifest.ts 75
clearToolCommandCache Function packages/core/src/toolchain/resolver.ts 184
parseToml Function packages/core/src/toolchain/toml.ts 278
findManifest Function packages/core/src/toolchain/manifest.ts 24
toolchainRoot Function packages/core/src/toolchain/resolver.ts 40
shimPath Function packages/core/src/toolchain/resolver.ts 44
resolveToolCommand Function packages/core/src/toolchain/resolver.ts 169
readTomlFile Function packages/core/src/toolchain/manifest.ts 15
asStringMap Function packages/core/src/toolchain/manifest.ts 85
loadManifest Function packages/core/src/toolchain/manifest.ts 37
loadPolicy Function packages/core/src/toolchain/project-reconcile.ts 124

Read the full file on GitHub · 95 lines

Changes

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.

  1. 2d ago First seen · 95 lines · 22 tokens per session scan A a3a1a17c9c67

Subscribe to this mod's changes

toolchain is a skill published in the GitHub repository princeofscale/bloxforge (5 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 1,282 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

unreal-asset-operation

Query and manage UE assets via UCP. Use when the user asks about asset search, dependencies, referencers, asset CRUD, asset management, getting selected/current assets, opening/closing asset editors, or any editor asset operation in Unreal Engine.

Italink/UnrealClientProtocol · 55 tokens

unreal-material-editing

Edit UE material node graphs and properties via text (ReadGraph/WriteGraph). Use when the user asks to add, remove, or rewire material expression nodes, or change material properties like ShadingModel or BlendMode.

Italink/UnrealClientProtocol · 51 tokens

unreal-actor-editing

Manage actors in UE levels via UCP. Use when the user asks to spawn, delete, move, duplicate, select, or otherwise manipulate actors in the Unreal Engine editor.

Italink/UnrealClientProtocol · 42 tokens

unreal-niagara-editing

Edit Niagara systems, emitters, and scripts via UCP. Use when the user asks to create/modify particle effects, manage emitters, configure modules, set module inputs, edit Niagara script graphs, or any Niagara VFX operation.

Italink/UnrealClientProtocol · 55 tokens

unreal-large-blueprint-analysis

Systematically analyze and translate large UE Blueprints (10+ functions) into C++ or other targets. Use when the user asks to convert a Blueprint to C++, audit a complex Blueprint, or understand a large Blueprint's full logic.

Italink/UnrealClientProtocol · 54 tokens

unreal-modeling-meshops

Skill "unreal-modeling-meshops" from Italink/UnrealClientProtocol, covering 建模 — 网格操作, 库, 修复函数, 修复结构体 and 简化函数.

Italink/UnrealClientProtocol · 48 tokens