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 commands/andronics/claude-plugin-typescript-pro/ts-reviewgit clone --depth 1 https://github.com/andronics/claude-plugin-typescript-proWrote 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/commands/andronics/claude-plugin-typescript-pro/ts-review)<a href="https://agentmods.dev/commands/andronics/claude-plugin-typescript-pro/ts-review"><img src="https://agentmods.dev/badge/commands/andronics/claude-plugin-typescript-pro/ts-review.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 | $0.00016 | $0.01012 |
| Opus 5 | $0.00008 | $0.00506 |
| Sonnet 5 | $0.00003 | $0.00202 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade A, and why
ts-review 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 4d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perform comprehensive TypeScript code review:
-
Determine Review Scope
- If $ARGUMENTS provided, review matching files
- If in git repository, review changed files (git diff)
- If reviewing PR, analyze all modified files
- Otherwise, review recently modified files or current file
-
Static Analysis
- Run TypeScript compiler:
tsc --noEmit - Run ESLint:
npm run lintornpx eslint - Check for type errors and warnings
- Identify disabled linting rules
- Run TypeScript compiler:
-
Type Safety Review
Check for:
- Usage of
anywithout justification - Type assertions (
as) that could be avoided -
@ts-ignorecomments (should be@ts-expect-error) - Missing return types on exported functions
- Implicit
anyfrom missing annotations - Proper null/undefined handling
- Type guards for runtime validation
- Exhaustive checking of discriminated unions
- Usage of
-
Code Quality Review
Naming & Readability:
- Clear, descriptive names
- Consistent naming conventions
- Self-documenting code
- Appropriate JSDoc for complex logic
Structure:
- Single responsibility per function
- No code duplication
- Proper separation of concerns
- Logical organization
Error Handling:
- Errors properly caught and handled
- Meaningful error messages
- No swallowed exceptions
- Custom error types for domain errors
-
TypeScript Best Practices
Check for:
-
constoverletwhere appropriate -
readonlyfor immutable data - Optional chaining (
?.) and nullish coalescing (??) -
async/awaitover raw promises - Array methods over imperative loops
- No
Function,Object,Boolean,Number,Stringtypes - No
enumfoot-guns (preferconstobjects) - Proper use of utility types (Partial, Pick, Omit, etc.)
-
satisfiesoperator for type validation (TS 4.9+)
-
-
Performance Analysis
Look for:
- Unnecessary re-renders (React)
- Missing memoization for expensive operations
- Inefficient algorithms (O(n²) loops)
- Memory leaks (event listeners, subscriptions)
- Type-system performance issues
- Overly complex type computations
-
Security Review
Check for:
- SQL injection vulnerabilities
- XSS vulnerabilities
- Unsafe eval() usage
- Credentials in code
- Missing input validation
- Type assertions bypassing security
anytypes in security-critical paths
-
Testing Coverage
Verify:
- Critical paths have tests
- Edge cases covered
- Tests are type-safe
- No disabled/skipped tests without reason
- Mocks properly typed
-
Generate Review Report
Organize findings by priority:
🔴 Blocking Issues (must fix before merge):
- Security vulnerabilities
- Type safety violations
- Breaking changes
- Critical bugs
🟡 Important Issues (should address):
- Type improvements
- Performance concerns
- Best practice violations
- Missing tests
🟢 Suggestions (nice to have):
- Refactoring opportunities
- Documentation improvements
- Style consistency
✅ Positive Feedback:
- Good practices observed
- Well-structured code
- Excellent type usage
-
Provide Actionable Feedback
For each issue:
- Show exact location (file:line)
- Explain the problem clearly
- Explain why it matters
- Provide concrete fix with code example
- Suggest alternatives if applicable
-
Summary
Provide:
- Overall code quality assessment
- Count of issues by category
- Estimated effort to address issues
- Recommendation: Approve, Request Changes, or Comment
- Next steps
Examples:
/ts-review- Review changed files/ts-review src/- Review directory/ts-review src/components/Button.tsx- Review specific file/ts-review --strict- Extra strict review
The review will be thorough, constructive, and educational, helping improve both the code and the developer's TypeScript skills.
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.
- 4d ago First seen · 146 lines · 16 tokens per session scan A f9d8b75e9247
ts-review is a command published in the GitHub repository andronics/claude-plugin-typescript-pro (4 stars, last pushed 10mo ago), licensed MIT. It adds 16 tokens to every session and 1,012 once invoked, about $0.0001 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 commands, from other repositories
types
Debug and fix TypeScript type errors with systematic analysis and expert guidance.
setup-code-intelligence
Check code-intelligence prerequisites (ripgrep + a language server) and print install hints.
type-crusade
Unleash parallel TypeScript Purist agents to purge every any, as cast, and type sin across the codebase. No type sin survives.
vite-react-setup
Setup project React SPA mới với Vite + TypeScript + Tailwind CSS v3 + Vitest. Dùng khi bắt đầu dự án frontend mới, cần scaffold đầy đủ config, brand KZTEK colors, và test setup sẵn sàng.
typescript
Apply TypeScript best practices and coding standards.
scaffold-react
Quickly scaffold a new React + TypeScript project with Claude Code configuration.