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/korbinjoe/teemai/code-reviewer-typescriptnpx skills add korbinjoe/TeemAI --skill code-reviewer-typescriptgit clone --depth 1 https://github.com/korbinjoe/TeemAIWrote 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/korbinjoe/teemai/code-reviewer-typescript)<a href="https://agentmods.dev/skills/korbinjoe/teemai/code-reviewer-typescript"><img src="https://agentmods.dev/badge/skills/korbinjoe/teemai/code-reviewer-typescript.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 | $0.00086 | $0.01671 |
| Opus 5 | $0.00043 | $0.00835 |
| Sonnet 5 | $0.00017 | $0.00334 |
| Haiku 4.5 | $0.00009 | $0.00167 |
Grade A, and why
code-reviewer-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 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Positioning
Focused on TypeScript language-level type system and code structure review. Checks whether types are rigorous, designs are sound, and modules are clear.
Difference from code-reviewer-react: React skill focuses on component design and Hooks; this skill focuses on TS type gymnastics and module design.
Difference from code-reviewer-nodejs: Node.js skill focuses on runtime behavior; this skill focuses on compile-time type safety.
Execution timing: When reviewing .ts files (non-React components)
Scan scope: Specified files, or file list obtained via git diff
Review Process
Step 1: Determine Review Scope
Determine files to review by priority:
- Files or directories explicitly specified by user
- User mentions PR or branch → run
git diff --name-only <base>..HEADto get changed files - User says "look at recent changes" → run
git diff --name-only HEAD~1 - None of the above → ask user which files to review
Only review .ts files. Skip test files (*.test.* / *.spec.*), type declaration files (*.d.ts), and config files.
For .tsx files, use the code-reviewer-react skill instead.
Step 2: Per-file Review
Read the complete file content first, understand context, then check each item. Execute the following review items for each file.
Step 3: Summary Report
Generate a structured report using the output template at the bottom.
Review Checklist
1. Type Safety
The type system is TypeScript's core value — loose types mean giving up compile-time protection.
Check items:
- Using
anytype → replace with specific type orunknown - Using non-null assertion
!→ use optional chaining?.or type guards instead - Using type assertion
asto bypass checks → check if there's a safer type narrowing approach - Whether
unknownis properly narrowed after use (typeof / instanceof / custom type guards) - Function parameters and return values have explicit types (exported functions must have explicit annotations)
- Whether implicit
anyexists (e.g., unannotated callback parameters, destructured assignments)
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 · 171 lines · 86 tokens per session scan A f0eb4240a505
code-reviewer-typescript is a skill published in the GitHub repository korbinjoe/TeemAI (2 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,671 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 2026-08-31.
Other skills, from other repositories
chat-sdk
Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI…
elizaos
Use when the task involves elizaOS core runtime concepts, plugins, actions, providers, evaluators, services, memories, state composition, or upstream elizaOS development. Covers the main abstractions and the TypeScript runtime mental model.
om-integration-tests
Run and create QA integration tests (Playwright TypeScript), including executing the full suite, converting optional markdown scenarios, and generating new tests from specs or feature descriptions. Defers all environment boot/reuse to the om-prepare-test-env skill and attaches to the shared descriptor it writes. Use…
freelance-gig-finder
Find fresh freelance and contract opportunities across multiple platforms for any skill set. Use this skill when a user asks "find me freelance React jobs", "Upwork gigs for Python developers", "freelance work posted this week", "contract jobs for designers", "find me remote freelance opportunities for [skill]", "I'm…
fetch
Default, free, and fastest way to read a URL's actual content — pulls clean, full page content (not a summary or a truncated snippet) as markdown, HTML, or structured JSON, including from JavaScript-heavy pages, in parallel across up to 10 URLs in one call. Zero setup, no CLI, no install — first use triggers an OAuth…
om-help
Open Mercato workflow navigator. Use when a developer or agent asks: "what should I do now?", "which skill should I use?", "where do I start?", "next steps?", "I'm lost", "what comes after X?", "how do I add/create/build Y in Open Mercato?", "where does Z go?", "what's the order for a feature/bugfix/PR?", "how do I do…