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/konamgil/mandu/typescript-ultimatenpx skills add konamgil/mandu --skill typescript-ultimategit clone --depth 1 https://github.com/konamgil/manduWrote 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/konamgil/mandu/typescript-ultimate)<a href="https://agentmods.dev/skills/konamgil/mandu/typescript-ultimate"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/typescript-ultimate.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 | $0.00074 | $0.00685 |
| Opus 5 | $0.00037 | $0.00342 |
| Sonnet 5 | $0.00015 | $0.00137 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
typescript-ultimate 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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Ultimate
Execute TypeScript work with maximum safety, clarity, and maintainability.
Workflow
-
Identify context first
- Determine runtime: Node / Browser / React / Next / Nest / Express / Fastify / Deno / RN.
- Determine strictness target: incremental vs strict-by-default.
- Determine risk class: API contract, persistence, auth, payments, migrations are high-risk.
-
Lock quality baseline before coding
- Apply strict compiler profile from
references/01-compiler-and-quality-baseline.md. - Apply lint and ordering rules from
references/07-code-review-and-standards.md. - Define typed boundaries for IO and external systems.
- Apply strict compiler profile from
-
Model domain types first
- Design discriminated unions for state and protocol variants.
- Use utility/mapped/conditional/template-literal types where they reduce duplication.
- Keep types readable; split deeply complex helpers into named aliases.
-
Implement with type-safe boundaries
- Parse unknown inputs to validated domain types.
- Keep
anyout of core paths. - Encode API request/response contracts in types.
-
Verify behavior + type contracts
- Add runtime tests + type tests (
tsc --noEmit, or expect-type style checks). - Add edge-case checks for nullability, narrowing, and exhaustive handling.
- Add runtime tests + type tests (
-
Review against production checklist
- Use
references/07-code-review-and-standards.mdreview rubric. - Prefer smallest safe change that improves type confidence.
- Use
Mandatory Rules
- Prefer
unknownoverany. - Prefer narrowing/type guards over assertions (
as). - Use discriminated unions for state machines and branching models.
- Keep imports organized and type-only imports explicit (
import type). - Use
constby default; avoid mutation when practical. - Use exhaustive checks (
never) for union switches. - Keep compiler+lint green before completion.
Reference Map
- Compiler/strict baseline:
references/01-compiler-and-quality-baseline.md - Type system patterns:
references/02-advanced-type-system.md - API/schema/contracts:
references/03-api-and-schema-typing.md - Framework-specific patterns:
references/04-framework-playbooks.md - Data/persistence/runtime boundaries:
references/05-data-and-runtime-boundaries.md - Testing strategy:
references/06-testing-types-and-behavior.md - Code review standards:
references/07-code-review-and-standards.md - Source corpus index (downloaded posts):
references/source-corpus-index.md
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- corpus/index.tsv 2.4 KB
- corpus/raw/0xbigboss__claude-code__typescript-best-practices.html 138 KB
- corpus/raw/alinaqi__claude-bootstrap__typescript.html 105 KB
- corpus/raw/asyrafhussin__agent-skills__typescript-react-patterns.html 123 KB
- corpus/raw/bmad-labs__skills__typescript-e2e-testing.html 132 KB
- corpus/raw/bobmatnyc__claude-mpm-skills__jest-typescript.html 480 KB
- corpus/raw/bobmatnyc__claude-mpm-skills__nodejs-backend-typescript.html 451 KB
- corpus/raw/bobmatnyc__claude-mpm-skills__trpc-type-safety.html 874 KB
- corpus/raw/bobmatnyc__claude-mpm-skills__typescript-core.html 104 KB
- corpus/raw/cexll__myclaude__prototype-prompt-generator.html 100 KB
- corpus/raw/dalestudy__skills__typescript.html 62 KB
- corpus/raw/davila7__claude-code-templates__openapi-to-typescript.html 123 KB
- corpus/raw/davila7__claude-code-templates__typescript-expert.html 143 KB
- corpus/raw/dotneet__claude-code-marketplace__typescript-react-reviewer.html 97 KB
- corpus/raw/giuseppe-trisciuoglio__developer-kit__typescript-docs.html 237 KB
- corpus/raw/jeffallan__claude-skills__typescript-pro.html 42 KB
- corpus/raw/jezweb__claude-skills__typescript-mcp.html 269 KB
- corpus/raw/jgeurts__eslint-config-decent__enforcing-typescript-standards.html 175 KB
- corpus/raw/jwynia__agent-skills__typescript-best-practices.html 131 KB
- corpus/raw/lobehub__lobe-chat__typescript.html 38 KB
- corpus/raw/lobehub__lobehub__typescript.html 38 KB
- corpus/raw/makfly__superpowers-symfony__symfony-form-types-validation.html 33 KB
- corpus/raw/martinholovsky__claude-skills-generator__typescript-expert.html 334 KB
- corpus/raw/metabase__metabase__typescript-review.html 33 KB
- corpus/raw/metabase__metabase__typescript-write.html 33 KB
- corpus/raw/mindrally__skills__deno-typescript.html 131 KB
- corpus/raw/mindrally__skills__expo-react-native-typescript.html 39 KB
- corpus/raw/mindrally__skills__express-typescript.html 146 KB
- corpus/raw/mindrally__skills__fastify-typescript.html 106 KB
- corpus/raw/mindrally__skills__nestjs-clean-typescript.html 37 KB
- corpus/raw/mindrally__skills__nextjs-react-typescript.html 37 KB
- corpus/raw/mindrally__skills__nextjs-typescript-tailwindcss-supabase.html 36 KB
- corpus/raw/mindrally__skills__nuxtjs-vue-typescript.html 38 KB
- corpus/raw/mindrally__skills__optimized-nextjs-typescript.html 38 KB
- corpus/raw/mindrally__skills__typeorm.html 299 KB
- corpus/raw/mindrally__skills__vuejs-typescript-best-practices.html 38 KB
- corpus/raw/openrouterteam__agent-skills__openrouter-typescript-sdk.html 431 KB
- corpus/raw/pproenca__dot-skills__typescript.html 70 KB
- corpus/raw/prowler-cloud__prowler__typescript.html 67 KB
- corpus/raw/rivet-dev__skills__rivetkit-typescript.html 623 KB
- corpus/raw/sickn33__antigravity-awesome-skills__javascript-typescript-typescript-scaffold.html 129 KB
- corpus/raw/sickn33__antigravity-awesome-skills__typescript-advanced-types.html 36 KB
- corpus/raw/sickn33__antigravity-awesome-skills__typescript-expert.html 144 KB
- corpus/raw/sickn33__antigravity-awesome-skills__typescript-pro.html 38 KB
- corpus/raw/siviter-xyz__dot-agent__typescript.html 46 KB
- corpus/raw/skillcreatorai__ai-agent-skills__javascript-typescript.html 93 KB
- corpus/raw/softaworks__agent-toolkit__openapi-to-typescript.html 123 KB
- corpus/raw/typefully__agent-skills__typefully.html 114 KB
- corpus/raw/wshobson__agents__python-type-safety.html 185 KB
- corpus/raw/wshobson__agents__typescript-advanced-types.html 368 KB
- corpus/raw/zhanghandong__rust-skills__m05-type-driven.html 63 KB
- corpus/text/0xbigboss__claude-code__typescript-best-practices.txt 8.7 KB
- corpus/text/alinaqi__claude-bootstrap__typescript.txt 4.9 KB
- corpus/text/asyrafhussin__agent-skills__typescript-react-patterns.txt 6.8 KB
- corpus/text/bmad-labs__skills__typescript-e2e-testing.txt 14 KB
- corpus/text/bobmatnyc__claude-mpm-skills__jest-typescript.txt 24 KB
- corpus/text/bobmatnyc__claude-mpm-skills__nodejs-backend-typescript.txt 22 KB
- corpus/text/bobmatnyc__claude-mpm-skills__trpc-type-safety.txt 46 KB
- corpus/text/bobmatnyc__claude-mpm-skills__typescript-core.txt 7.6 KB
- corpus/text/cexll__myclaude__prototype-prompt-generator.txt 19 KB
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.
- 5d ago First seen · 67 lines · 74 tokens per session scan A 36cfd1d03fa0
typescript-ultimate is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 8d ago), licensed MPL-2.0. It adds 74 tokens to every session and 685 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 2026-08-30.
Other skills, from other repositories
widen-return-type
When delegating a task affected by this skill, include.
bun
Use this skill when building with Bun runtime — Bun APIs, testing, package management, shell scripting, hot reload, SQLite, file I/O. This skill enforces: built-in APIs over npm equivalents, Bun test runner, bun install speed optimization, Bun.shell for scripts. Do NOT use for: Node.js-specific APIs…
mastra
Comprehensive Mastra framework guide. Teaches how to find current documentation, verify API signatures, and build agents and workflows. Covers documentation lookup strategies (embedded docs, remote docs), core concepts (agents vs workflows, tools, memory, RAG), TypeScript requirements, and common patterns. Use this…
sruja-project
Procedural workflows for working with the Sruja codebase. Teaches AI editors how to add components, validate changes, and follow patterns.
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…
hono-core
Hono ultrafast web framework fundamentals - routing, context, handlers, and response patterns for multi-runtime deployment.