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 skills add WrongStack/WrongStack --skill typescript-strictgit clone --depth 1 https://github.com/WrongStack/WrongStackWrote 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/wrongstack/wrongstack/typescript-strict)<a href="https://agentmods.dev/skills/wrongstack/wrongstack/typescript-strict"><img src="https://agentmods.dev/badge/skills/wrongstack/wrongstack/typescript-strict/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wrongstack/wrongstack/typescript-strict"><img src="https://agentmods.dev/badge/skills/wrongstack/wrongstack/typescript-strict.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.01689 |
| Opus 5.5 | $0.00037 | $0.00676 |
| Sonnet 5.5 | $0.00018 | $0.00338 |
| Haiku 4.5 | $0.00009 | $0.00169 |
Grade A, and why
typescript-strict 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 today.
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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Strict
Selection card
- Task: TypeScript contracts and narrowing without any.
- Start: Locate the affected route/component and its runtime/lockfile.
- Finish: apply the acceptance checks below; report observed results and unresolved constraints.
Overview
Target TypeScript 7.0.2, verified from npm on 2026-10-09. Static types protect compile-time contracts; external data still needs runtime validation. Work within the project strictness and module-resolution contract.
Rules
- Pre-flight: Inspect repo
tsconfig.json& live TypeScript version first. Checkpackage.jsonfor the installedtypescriptversion and inspect the project'stsconfig.json. Queryregistry.npmjs.org/typescript/latestbefore recommending modern compiler flags (e.g.isolatedDeclarationsin TS 5.5+,satisfiesin TS 4.9+) to ensure compiler compatibility. - Respect the project's
tsconfig. Write code that passes the flags it has. Tightening flags repo-wide is a separate, requested change — it can surface hundreds of errors. - Fix type errors, don't silence them. No
as any, noas unknown as T, no@ts-ignore; a@ts-expect-errorneeds a comment explaining why. - Choose satisfies when validating an inferred expression without replacing its inferred type; keep intentional annotations/widening where the contract needs them.
- Validate at trust boundaries. JSON, network responses, environment, and user
input arrive as
unknownand are narrowed by Zod, TypeBox, or explicit type guards. - Prefer narrowing to assertion. A non-null
!or anascast is acceptable only where the invariant is locally obvious and a check would be noise. - Model finite states as discriminated unions, and end exhaustive switches with
a
nevercheck so a new variant fails to compile. - Always handle potential
undefinedsafely whennoUncheckedIndexedAccessis active. - Annotate the return types of exported functions (
isolatedDeclarationscompliance); inference is fine inside private helpers.
What ships with it
1 file 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.
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.
- today Changed · +1 lines 8d2120c99722
- 10d ago Changed cc85b7975382
- 11d ago Changed · +26 lines d97a4ae09792
- 1mo ago Changed · -141 lines · +29 tokens per session 41a34e04ba74
- 1mo ago First seen · 273 lines · 63 tokens per session scan A 82c56593ca13
typescript-strict is a skill published in the GitHub repository WrongStack/WrongStack (388 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,689 once invoked, about $0.0004 per session on Opus 5.5. 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
ai-provider-anthropic-sdk
Official Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, vision, extended thinking, structured outputs, prompt caching, batch API, and production best practices.
ai-infrastructure-ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint.
ai-infrastructure-replicate
Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training.
ai-infrastructure-together-ai
Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation, fine-tuning, and OpenAI-compatible endpoints.
ai-orchestration-llamaindex
LlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows in TypeScript.
ai-provider-cohere-sdk
Official Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, streaming, and model selection.