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 cosmix/loom --skill loom-typescriptgit clone --depth 1 https://github.com/cosmix/loomWrote 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/cosmix/loom/loom-typescript)<a href="https://agentmods.dev/skills/cosmix/loom/loom-typescript"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-typescript/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/cosmix/loom/loom-typescript"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-typescript.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 613 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Excessive Agency · line 200 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 307 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00016 | $0.11225 |
| Opus 5.5 | $0.00006 | $0.04490 |
| Sonnet 5.5 | $0.00003 | $0.02245 |
| Haiku 4.5 | $0.00002 | $0.01123 |
Grade A, and why
loom-typescript 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 24d 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 — 850 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Language Expertise
Overview
Type-safe, production-quality TypeScript: the type system's sharp edges, strict-mode config that actually moves the needle, the type-vs-runtime boundary, and framework patterns (zod/tRPC/Prisma/React/Express). Assumes fluency with JS and basic TS — this is reference for the traps and idioms that bite experienced engineers.
Toolchain assumed throughout: Bun (install/run/test), Vite (app dev server and bundler — Rolldown bundling, Oxc transforms and minifier, Lightning CSS), tsdown (library bundler on Rolldown), oxlint (lint), oxfmt (format), tsc --noEmit (type-check). ESLint, Prettier, esbuild, and Babel are the legacy equivalents — do not add them to a project that has this stack. See Toolchain below.
Type System Essentials
Generics
// Constraints + default type param; `this` return for fluent chaining
interface HasId { id: string }
class Repo<T extends HasId = HasId> {
private items = new Map<string, T>();
save(item: T): this { this.items.set(item.id, item); return this; }
find(id: string): T | undefined { return this.items.get(id); }
}
// Return `as const` to preserve a tuple/literal shape instead of widening
function pair<A, B>(a: A, b: B) { return [a, b] as const; } // readonly [A, B]
Utility types
| Utility | Result |
|---|---|
Partial<T> / Required<T> |
all props optional / required |
Readonly<T> |
all props readonly (shallow) |
Pick<T,K> / Omit<T,K> |
keep / drop keys K |
Record<K,V> |
object with keys K, values V |
Extract<U,V> / Exclude<U,V> |
keep / drop union members of U assignable to V |
NonNullable<T> |
strip null / undefined |
ReturnType<F> / Parameters<F> |
function return type / param tuple |
Awaited<T> |
recursively unwrap Promise (prefer over a hand-rolled Unwrap) |
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.
- 24d ago Changed · +43 lines 4149806f91c9
- 1mo ago Changed · -1 lines e9b798244117
- 1mo ago First seen · 808 lines · 16 tokens per session scan A 20bfcc87b60b
loom-typescript is a skill published in the GitHub repository cosmix/loom (62 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 11,225 once invoked, about $0.0001 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
aws-lambda-typescript-integration
Provides AWS Lambda integration patterns for TypeScript with cold start optimization. Use when creating or deploying TypeScript Lambda functions, choosing between NestJS framework and raw TypeScript approaches, optimizing cold starts, configuring API Gateway or ALB integration, or implementing serverless TypeScript…
aws-cdk
Provides AWS CDK TypeScript patterns for defining, validating, and deploying AWS infrastructure as code. Use when creating CDK apps, stacks, and reusable constructs, modeling serverless or VPC-based architectures, applying IAM and encryption defaults, or testing and reviewing cdk synth, cdk diff, and cdk deploy…
typescript-security-review
Provides security review capability for TypeScript/Node.js applications, validates code against XSS, injection, CSRF, JWT/OAuth2 flaws, dependency CVEs, and secrets exposure. Use when performing security audits, before deployment, reviewing authentication/authorization implementations, or ensuring OWASP compliance for…
dynamodb-toolbox-patterns
Provides TypeScript patterns for DynamoDB-Toolbox v2 including schema/table/entity modeling, .build() command workflow, query/scan access patterns, batch and transaction operations, and single-table design with computed keys. Use when implementing type-safe DynamoDB access layers with DynamoDB-Toolbox v2 in TypeScript…
typescript-docs
Generates comprehensive TypeScript documentation using JSDoc, TypeDoc, and multi-layered documentation patterns for different audiences. Use when creating API documentation, architectural decision records (ADRs), code examples, and framework-specific patterns for NestJS, Express, React, Angular, and Vue.
zod-validation-utilities
Creates reusable Zod v4 schemas, validates API payloads, forms, and configuration input, transforms and coerces data safely, and handles validation errors with strong type inference for TypeScript applications. Use when designing validation layers, parsing z.string(), z.object(), or z.email() schemas, or implementing…