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 skills/softspark/ai-toolkit/typescript-rulesnpx skills add softspark/ai-toolkit --skill typescript-rulesgit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/typescript-rules)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/typescript-rules"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/typescript-rules.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 | $0.00060 | $0.02528 |
| Opus 5 | $0.00030 | $0.01264 |
| Sonnet 5 | $0.00012 | $0.00506 |
| Haiku 4.5 | $0.00006 | $0.00253 |
Grade A, and why
typescript-rules 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 yesterday.
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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript/JavaScript Rules
These rules come from app/rules/typescript/ in ai-toolkit. They cover
the project's standards for coding style, frameworks, patterns,
security, and testing in TypeScript/JavaScript. Apply them when writing or
reviewing TypeScript/JavaScript code.
TypeScript Coding Style
Strict Mode
- Always use
strict: truein tsconfig.json. - Never use
any-- useunknown+ type guards instead. - Prefer
interfaceovertypefor object shapes (extendable). - Use
as constfor literal types and readonly tuples.
Naming
- PascalCase: types, interfaces, enums, classes, components.
- camelCase: variables, functions, methods, properties.
- UPPER_SNAKE: constants, env vars.
- Prefix interfaces with
Ionly if project convention requires it.
Functions
- Prefer arrow functions for callbacks and inline.
- Use
functiondeclarations for hoisted, named functions. - Max 3 parameters -- use options object beyond that.
- Always type return values for public/exported functions.
Imports
- Group: node builtins, external, internal, relative.
- Use
typeimports:import type { Foo } from './foo'. - No barrel exports unless at package boundary.
- Prefer named exports over default exports.
Types
- Use discriminated unions over class hierarchies for state.
- Use
readonlyfor arrays and objects that should not be mutated. - Use
satisfiesoperator to validate types without widening. - Prefer
unknownoveranyat API boundaries. - Use template literal types for string patterns.
Avoid
enum-- useas constobjects or union types.namespace-- use ES modules.privatekeyword -- use#private fields.- Non-null assertion
!-- use proper type narrowing. astype casting -- use type guards and narrowing.
Configuration
- Enable
noUncheckedIndexedAccessfor safer array/object access. - Enable
exactOptionalPropertyTypesto distinguishundefinedfrom missing. - Use
moduleResolution: "bundler"for modern projects. - Set
isolatedModules: truefor bundler compatibility.
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.
- yesterday First seen · 250 lines · 60 tokens per session scan A 83948ca55c87
typescript-rules is a skill published in the GitHub repository softspark/ai-toolkit (169 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 2,528 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
adk
Use this skill when you've got questions about the Botpress Agent Development Kit (ADK) - like when you're building a feature that involves tables, actions, tools, workflows, conversations, files, knowledge bases, triggers, or Zai.
typescript-check
TypeScript type checking via tsc --noEmit with actionable error output.
vitest-runner
Run Vitest tests and parse results into actionable output.
valibot
Repository guidance for using Valibot as the schema validation library within the hr-skills monorepo. Use when writing or modifying schemas in packages/hr-skills-ref/src/schema.ts or packages/hr-skills-build/src/shared/schema.ts, when validating parsed YAML frontmatter, when handling safeParse results, or when…
typescript
Repository guidance for writing, reviewing, and maintaining TypeScript code within the hr-skills monorepo. Covers project conventions, compiler settings, module structure, and development workflows.
typescript-development
You MUST activate this skill when working on TypeScript or JavaScript projects.