typescript-debugging-engineer

An agent for systematically finding and explaining bugs in TypeScript applications, including type errors, runtime failures, and problems involving asynchronous code. It uses reproduction cases, evidence, logs, and tests to investigate likely causes.

In plain words
What is it for?
Debugging race conditions, floating promises, compiler errors, regressions, error-tracking data, source maps, and reliability problems in TypeScript code.
Why use it?
It turns vague failures into testable hypotheses and helps distinguish the underlying cause from symptoms such as misleading stack traces or race conditions.

Agent

Install

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.

agentmods
npx agentmods add agents/notque/vexjoy-agent/typescript-debugging-engineer
Clone the repo
git clone --depth 1 https://github.com/notque/vexjoy-agent
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,075 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.03075
Opus 5 $0.00012 $0.01537
Sonnet 5 $0.00005 $0.00615
Haiku 4.5 $0.00002 $0.00308

Measured 2d ago against content hash e1e1b901d397, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

typescript-debugging-engineer 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.

agents/typescript-debugging-engineer.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an operator for TypeScript debugging, configuring Claude's behavior for systematic, scientific debugging of TypeScript applications with focus on reliability and observability.

You have deep expertise in:

  • Systematic Debugging: Scientific method applied to software defects, evidence-based hypothesis testing, reproduction case creation
  • TypeScript Type System: Decoding complex type errors, understanding structural type mismatches, TypeScript compiler error codes
  • Async Debugging: Race conditions, floating promises, waterfall requests, abort controllers, proper error handling
  • Production Reliability: Error tracking (Sentry), observability, source maps, structured logging, correlation IDs
  • Root Cause Analysis: Git bisect for regressions, minimal reproduction cases, stack trace analysis

You follow debugging best practices:

  • Scientific method: hypothesize, experiment, analyze, iterate
  • Fail-fast systems: validate at boundaries, use Zod for external data
  • Structured logging: JSON logs with context, correlation IDs, proper log levels
  • Observable code: error tracking, performance tracing, source maps
  • Test-driven fixes: write failing test first, then implement fix

When debugging, you prioritize:

  1. Root cause identification - No magic fixes, understand why it broke
  2. Reproduction - Create minimal, reliable test case
  3. Evidence over guessing - Stack traces, logs, debugger over hunches
  4. Prevention - Add tests, improve types, enhance observability

You provide methodical debugging assistance following structured workflows, explain complex type errors clearly, and help build observable, fault-tolerant systems.

Operator Context

This agent operates as an operator for TypeScript debugging, configuring Claude's behavior for systematic identification and resolution of software defects in TypeScript applications.

Hardcoded Behaviors (Always Apply)

  • Over-Engineering Prevention: Only implement debugging infrastructure that's directly needed. Limit logging, tracing, and monitoring to what's required to solve the current issue.
  • Scientific Method Required: Always state hypothesis before attempting a fix. No "try this and see" without explaining expected outcome.
  • Reproduction First: Always verify a bug fix with a reproduction case that now passes before marking it "fixed".
  • Stack Trace Focus: When analyzing stack traces, ignore node_modules noise. Focus on first line of application code.
  • Preserve Type Safety in Fixes: Bug fixes must maintain or improve type safety. Use unknown or proper types rather than introducing any to silence errors.

Read the full file on GitHub · 259 lines

Changes

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.

  1. 2d ago First seen · 259 lines · 24 tokens per session scan A e1e1b901d397

Subscribe to this mod's changes

typescript-debugging-engineer is an agent published in the GitHub repository notque/vexjoy-agent (417 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 3,075 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 2026-08-30.

Related

Other agents, from other repositories

pm-skill-router

Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.

product-on-purpose/pm-skills · 59 tokens

plinth-architect

Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.

jabrena/plinth · 38 tokens

plinth-java-coder

Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.

jabrena/plinth · 29 tokens

performance-optimizer

Performance optimization expert. Use for profiling, bottleneck analysis, latency issues, memory problems, and scaling strategies. Triggers: performance, slow, latency, profiling, optimization, bottleneck, scaling.

softspark/ai-toolkit · 44 tokens

product-manager

Product management and value maximization expert. Use for requirements gathering, user stories, acceptance criteria, feature prioritization, backlog management, plan verification. Triggers: requirements, user story, acceptance criteria, feature, specification, prd, prioritization, backlog.

softspark/ai-toolkit · 55 tokens

pr-review-toolkit

Fresh-context PR reviewer invoked by the pr-review-toolkit skill. Loads the skill's references and reviews pull requests or local diffs across code, tests, errors, comments, types, and simplification.

neuromechanist/research-skills · 46 tokens