build-tool

A build workflow for creating calculator tools according to a repository's specification-first, four-file convention. It is designed for sites whose calculators must follow documented formulas, inputs, validation, and outputs.

In plain words
What is it for?
Use it to specify and build a new calculator, including its formula, assumptions, input ranges, validation, output contract, hand-checked scenarios, known deviations, and out-of-scope cases.
Why use it?
It reduces errors caused by coding a calculator before its rules and reference examples are written down.

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/jared833/claude-code-hooks/build-tool
Any agent
npx skills add jared833/claude-code-hooks --skill build-tool
Clone the repo
git clone --depth 1 https://github.com/jared833/claude-code-hooks

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,171 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 $0.00046 $0.01171
Opus 5 $0.00023 $0.00585
Sonnet 5 $0.00009 $0.00234
Haiku 4.5 $0.00005 $0.00117

Measured 2d ago against content hash 95b17a19fc32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-tool 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.

skills/build-tool/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

build-tool

Checklist for building one calculator tool. This one comes from a site of NEC electrical calculators, so the domain language is electrical, but the shape holds for any site whose tools have to be right rather than pretty.

Authoritative references live in the repo this runs against. Read them, do not duplicate them. The paths below are that repo's; substitute your own.

  • CLAUDE.md for accuracy principles, voice rules, the mandatory 7-part page template, exact disclaimer text, compliance flags.
  • docs/voltage-drop-spec.md for the reference spec format.
  • Your own release playbook for everything after the build. This skill covers spec plus build and stops there. See pipeline/ in this repo for the shape of one.

1. Spec first

Write docs/specs/<slug>-spec.md modeled on the reference spec: identity (name, slug, target keyword, NEC edition + exact tables/articles), formula derivation with stated assumptions, inputs (ranges/units/validation), output contract, 5 to 10 hand-derived reference scenarios with arithmetic shown, documented deviations from third-party tools, v1 out-of-scope list.

2. Four files

File Notes
site/src/lib/calculators/<slug>.js Pure functions only. Comment header cites the NEC table/formula + edition + assumptions.
site/src/lib/calculators/<slug>.test.js Vitest. The spec's 5 to 10 scenarios, arithmetic in comments, at least 1 cross-checked against a named independent tool.
site/src/components/tools/<slug>-tool.astro Interactive UI, vanilla JS in <script>. No frameworks. Tool fully visible above the fold.
site/src/pages/<slug>.astro 7-part template; meta object (title with keyword + brand, about 60 chars; 120 to 155 char description; keyword; canonical optional, Layout derives the trailing-slash form); WebApplication + FAQPage JSON-LD.

Color. Two roles, declared in site/src/styles/global.css and enforced by npm run check:accent. Blue is action: the Calculate button, focus rings, the result hero, in-content links. Amber is identity: the brand shell, cards, eyebrows, callouts. In a scoped <style> block read the tokens (var(--action), var(--action-hover), var(--action-text)) rather than writing a hex, and copy the block from an existing tool instead of inventing one. Never put white text on amber, it is 2.15:1 and fails AA.

Read the full file on GitHub · 89 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 · 89 lines · 46 tokens per session scan A 95b17a19fc32

Subscribe to this mod's changes

build-tool is a skill published in the GitHub repository jared833/claude-code-hooks (2 stars, last pushed 13d ago), licensed MIT. It adds 46 tokens to every session and 1,171 once invoked, about $0.0002 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens