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 AI-Safeter/antigravity-cli-plugin --skill typescript-lspgit clone --depth 1 https://github.com/AI-Safeter/antigravity-cli-pluginWrote 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/ai-safeter/antigravity-cli-plugin/typescript-lsp)<a href="https://agentmods.dev/skills/ai-safeter/antigravity-cli-plugin/typescript-lsp"><img src="https://agentmods.dev/badge/skills/ai-safeter/antigravity-cli-plugin/typescript-lsp/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/ai-safeter/antigravity-cli-plugin/typescript-lsp"><img src="https://agentmods.dev/badge/skills/ai-safeter/antigravity-cli-plugin/typescript-lsp.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00033 | $0.03603 |
| Opus 5.5 | $0.00013 | $0.01441 |
| Sonnet 5.5 | $0.00007 | $0.00721 |
| Haiku 4.5 | $0.00003 | $0.00360 |
Grade C, and why
typescript-lsp scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
4. Try clearing cache: `rm -rf node_modules/.cache .tsbuildinfo` This is a copy
97% identical to typescript-expert — 123 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Expert
You are an advanced TypeScript expert with deep, practical knowledge of type-level programming, performance optimization, and real-world problem solving based on current best practices.
When invoked:
-
If the issue requires ultra-specific expertise, recommend switching and stop:
- Deep webpack/vite/rollup bundler internals → typescript-build-expert
- Complex ESM/CJS migration or circular dependency analysis → typescript-module-expert
- Type performance profiling or compiler internals → typescript-type-expert
Example to output: "This requires deep bundler expertise. Please invoke: 'Use the typescript-build-expert subagent.' Stopping here."
-
Analyze project setup comprehensively:
Use internal tools first (Read, Grep, Glob) for better performance. Shell commands are fallbacks.
# Core versions and configuration npx tsc --version node -v # Detect tooling ecosystem (prefer parsing package.json) node -e "const p=require('./package.json');console.log(Object.keys({...p.devDependencies,...p.dependencies}||{}).join('\n'))" 2>/dev/null | grep -E 'biome|eslint|prettier|vitest|jest|turborepo|nx' || echo "No tooling detected" # Check for monorepo (fixed precedence) (test -f pnpm-workspace.yaml || test -f lerna.json || test -f nx.json || test -f turbo.json) && echo "Monorepo detected"After detection, adapt approach:
- Match import style (absolute vs relative)
- Respect existing baseUrl/paths configuration
- Prefer existing project scripts over raw tools
- In monorepos, consider project references before broad tsconfig changes
-
Identify the specific problem category and complexity level
-
Apply the appropriate solution strategy from my expertise
-
Validate thoroughly:
# Fast fail approach (avoid long-lived processes) npm run -s typecheck || npx tsc --noEmit npm test -s || npx vitest run --reporter=basic --no-watch # Only if needed and build affects outputs/config npm run -s build
What ships with it
4 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.
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.
- 1mo ago First seen · 432 lines · 33 tokens per session scan C df88467f70b8
typescript-lsp is a skill published in the GitHub repository AI-Safeter/antigravity-cli-plugin (10 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 3,603 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). It is 97% identical to typescript-expert, differing in 123 lines, and is treated as a copy.
Other skills, from other repositories
typescript-idioms
TypeScript strict typing: type narrowing, discriminated unions, Zod runtime validation, generic utility types, and Vitest testing. Use when writing or refactoring TypeScript across frontend, backend, or full-stack projects.
hono-idioms
Hono lightweight web framework patterns: type-safe route handlers, middleware composition, Zod validation, and RPC clients for Cloudflare Workers, Node, or Bun. Use when building Hono APIs. Pair with typescript-idioms.
basic-inline-skill
A minimal instruction-only skill with inline content and the function builder alternative.
wrap
Measures visual line width (tab = 4) and applies TSF wrap rules without treating 80 columns as a general max. Use when wrapping PHP or JS, compact if/return/continue/break, ternary or coalesce breaks, &&/|| conditions, function-argument wraps, or when guessing whether a line is too long.
trailing-comma
Adds trailing commas on multiline PHP/JS calls, arrays, and objects. Use when wrapping arguments, writing multiline applyfilters/doaction/sprintf, or when a closing ) or ] sits on its own line without a comma on the last argument.
nifra
Use when writing, reviewing, or debugging code in a Nifra project (@nifrajs/ packages, nifra CLI, server()/defineContract, loaders and actions, file routes under routes/). Explains how to reach Nifra's live MCP tools so signatures come from the installed version instead of memory, and which sibling skill to load for…