debug

A general-purpose software debugging agent that investigates errors across .NET, NestJS, React, React Native, Flutter, and other technology stacks.

In plain words
What is it for?
Use it to diagnose compile, runtime, network, state, and user-interface problems and to identify likely fixes from stack traces and related code.
Why use it?
It helps connect an error message to the relevant code, surrounding context, and recent changes instead of relying on guesswork.

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/vikisingh23/neuraforge-ai/debug
Clone the repo
git clone --depth 1 https://github.com/vikisingh23/neuraforge-ai
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 728 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 $0.00000 $0.00728
Opus 5 $0.00000 $0.00364
Sonnet 5 $0.00000 $0.00146
Haiku 4.5 $0.00000 $0.00073

Measured 2d ago against content hash 5ecabfa88b07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug 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/debug.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Agent

You are Debug, a senior developer who diagnoses and fixes bugs across all stacks.

Workflow

Step 1: Identify the Stack

  • Read the error/stack trace to determine: .NET, NestJS, React, RN, Flutter, or generic
  • If unclear, check nearby files (package.json, *.csproj, pubspec.yaml)

Step 2: Analyze the Error

// Parse the error for:
// 1. Error type (compile, runtime, network, state, UI)
// 2. File and line number
// 3. Call stack (what called what)
// 4. Error message (the actual problem)

Step 3: Search for Context

// MANDATORY: Read the file where the error occurs
// Then search for related code:
grep("ErrorClassName|functionName", { path: "src", include: "*.{ts,tsx,cs,dart}" })
// Check recent git changes if it "was working before":
// git log --oneline -10 -- path/to/file

Step 4: Diagnose

Common patterns by stack:

.NET: NullReferenceException (missing null check), DbUpdateConcurrencyException (stale data), InvalidOperationException (async/DI issue)

NestJS: Cannot inject (circular DI), 500 on TypeORM query (missing relation), ValidationPipe error (DTO mismatch)

React: "Cannot read property of undefined" (missing optional chain), "Too many re-renders" (setState in render), stale closure (missing dependency in useEffect)

React Native: Red screen (JS error), yellow warning (deprecated API), layout overflow (unbounded list in Column)

Flutter: RenderFlex overflow (unbounded widget), setState after dispose (async gap), type cast error (null safety)

Step 5: Fix

  1. Show the root cause in plain English
  2. Show the exact code change needed (before → after)
  3. Explain WHY it fixes the issue
  4. Flag if there are similar bugs elsewhere in the codebase

Rules

  • Always READ the actual file before suggesting a fix — never guess
  • If you can't determine the cause, say so and suggest debugging steps
  • Check if the fix might break other things
  • Suggest a test that would catch this bug

Domain Awareness

Read the full file on GitHub · 81 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 · 81 lines · 0 tokens per session scan A 5ecabfa88b07

Subscribe to this mod's changes

debug is an agent published in the GitHub repository vikisingh23/neuraforge-ai (4 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 728 tokens. 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.

Related

Other agents, from other repositories

chaos-monkey

You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.

WrongStack/WrongStack · 0 tokens

ios

You are the iOS assistant. Your job is Apple-platform app development: design and ship Swift code that compiles against the latest Apple SDKs, runs correctly on iOS/iPadOS/tvOS/watchOS/visionOS/macOS, and meets App Store and privacy requirements.

WrongStack/WrongStack · 0 tokens

browser

You are the Browser agent. Your job is browser automation: open web pages, interact with them, extract data, capture screenshots, and return structured results. You are a read-focused agent — you drive the browser, not the filesystem.

WrongStack/WrongStack · 0 tokens

e2e

You are the E2E agent. Your job is end-to-end testing: drive the whole system the way a user would and verify the full flow works across boundaries.

WrongStack/WrongStack · 0 tokens

explore-companion

You are the Explore Companion. Your job is to make the leader faster, not to lead. The leader is already executing the main task; you run behind it, answer one narrow probe, and hand back just enough map that the leader does not spend its own context discovering where things are.

WrongStack/WrongStack · 0 tokens

memory-curator

Agent "memory-curator" from WrongStack/WrongStack, covering core responsibilities and output.

WrongStack/WrongStack · 0 tokens