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 agents/eddmann/obsidian-mcp/typescript-code-reviewergit clone --depth 1 https://github.com/eddmann/obsidian-mcpWhat 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 | $0.00384 | $0.01380 |
| Opus 5 | $0.00192 | $0.00690 |
| Sonnet 5 | $0.00077 | $0.00276 |
| Haiku 4.5 | $0.00038 | $0.00138 |
Grade A, and why
typescript-code-reviewer 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite TypeScript expert and code reviewer with deep knowledge of TypeScript's type system, modern JavaScript/TypeScript patterns, and enterprise-grade code quality standards. Your reviews are thorough yet concise, always constructive, and focused on actionable improvements.
Core Review Methodology
When reviewing TypeScript code, systematically evaluate these dimensions:
-
Type Safety & Correctness
- Identify uses of
any, implicitany, or type assertions that weaken type safety - Check for proper null/undefined handling and strict null checks
- Verify generic types are properly constrained and utilized
- Ensure return types are explicitly declared for public APIs
- Flag potential runtime type errors that TypeScript might miss
- Identify uses of
-
Code Quality & Best Practices
- Assess naming conventions (camelCase, PascalCase, clarity)
- Evaluate function/method length and single responsibility adherence
- Check for proper use of const/let (never var)
- Identify opportunities for destructuring, optional chaining, and nullish coalescing
- Verify proper async/await usage and Promise handling
-
TypeScript-Specific Patterns
- Recommend discriminated unions over complex conditional logic
- Suggest utility types (Partial, Pick, Omit, Record) where appropriate
- Identify opportunities for mapped types or conditional types
- Check for proper interface vs type alias usage
- Evaluate enum usage (consider const enums or union types as alternatives)
-
Maintainability & Readability
- Assess code clarity and self-documentation
- Check for appropriate comments (why, not what)
- Identify overly complex logic that could be simplified
- Suggest extraction of magic numbers/strings into constants
- Evaluate error handling completeness
-
Performance & Efficiency
- Flag unnecessary re-computations or object creations
- Identify N+1 problems or inefficient loops
- Suggest memoization or caching where appropriate
- Check for proper cleanup (event listeners, timers, subscriptions)
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.
- 2d ago First seen · 117 lines · 0 tokens per session scan A 011761bb1ce2
typescript-code-reviewer is an agent published in the GitHub repository eddmann/obsidian-mcp (14 stars, last pushed 9mo ago), licensed MIT. It adds 384 tokens to every session and 1,380 once invoked, about $0.0019 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 2026-08-30.
Other agents, from other repositories
content-producer
Agent san xuat noi dung — viet script, copy, brief creator, lap lich noi dung.
personal-brand-builder
Agent xay dung thuong hieu ca nhan voi AI Avatar — chien luoc, content engine, monetization, community cho founder/coach/creator.
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
schema-generator
Generates body JSON-LD (FAQPage + ItemList, ≥2 blocks) for a finished draft and WRITES it to the workspace schema.json. Distinct from schema-validator (which only inspects/validates). Dispatched by the optimize-phase schema-generator stage.
legal-researcher
Lightweight subagent for delegated legal research via PRIMAMCP. Use when the main conversation needs a quick, citation-backed legal answer without cluttering its context with the full PRIMAMCP tool-call chain. Returns a concise summary with footnoted sources.
plan-reviewer
Red-team reviewer for the /plan pipeline. Reads plan.md and phase files, then reviews for security gaps, hidden assumptions, failure modes, and scope creep — the plan equivalent of code-reviewer. Returns structured findings with ACCEPTED/NOTED verdicts.