Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TechyMT/claude-code-superpowersnpx agentmods add skills/techymt/claude-code-superpowers/build-tool-factoryWrote 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/techymt/claude-code-superpowers/build-tool-factory)<a href="https://agentmods.dev/skills/techymt/claude-code-superpowers/build-tool-factory"><img src="https://agentmods.dev/badge/skills/techymt/claude-code-superpowers/build-tool-factory.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.01966 |
| Opus 5 | $0.00043 | $0.00983 |
| Sonnet 5 | $0.00017 | $0.00393 |
| Haiku 4.5 | $0.00009 | $0.00197 |
Grade A, and why
build-tool-factory 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 6d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
buildTool() Factory
The pattern
Factory functions for capability objects solve a common problem: a typed interface has many methods, but any given implementation only needs to override a few. Listing all methods explicitly creates noise and makes the "what does this tool actually do" harder to see. A factory fills in safe defaults and lets the author focus on the non-trivial fields.
The pattern has three parts: (1) a minimal definition type (ToolDef) where defaultable methods are optional, (2) a factory (buildTool) that merges your definition with safe defaults, and (3) lazy schema getters so schemas are built on first access, not at module load time.
// DefaultableToolKeys — methods buildTool fills in with safe defaults
type DefaultableToolKeys =
| 'isEnabled'
| 'isConcurrencySafe'
| 'isReadOnly'
| 'isDestructive'
| 'checkPermissions'
| 'toAutoClassifierInput'
| 'userFacingName'
// ToolDef — what you pass to buildTool (same as Tool but defaultable methods are optional)
export type ToolDef<
Input extends AnyObject = AnyObject,
Output = unknown,
P extends ToolProgressData = ToolProgressData,
> = Omit<Tool<Input, Output, P>, DefaultableToolKeys> &
Partial<Pick<Tool<Input, Output, P>, DefaultableToolKeys>>
// buildTool fills in safe defaults for all DefaultableToolKeys
export function buildTool<D extends ToolDef>(def: D): BuiltTool<D>
| Default key | Safe default value |
|---|---|
isConcurrencySafe |
() => false |
isReadOnly |
() => false |
isDestructive |
() => false |
checkPermissions |
{ behavior: 'allow' } |
isEnabled |
() => true |
userFacingName |
derived from name |
Why this matters
Claude Code has ~30 tools. Each shares the same set of safety defaults: assume not concurrent-safe, assume not read-only, assume not destructive, assume checkPermissions passes through. Without a factory, every new tool must explicitly declare all of these even when the intent is "no override". The factory encodes the security-safe posture as the default: new tools are restrictive until explicitly opted out.
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.
- 6d ago First seen · 181 lines · 85 tokens per session scan A 93579ef6db7b
build-tool-factory is a skill published in the GitHub repository TechyMT/claude-code-superpowers (5 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 1,966 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…