bug-solver-agent

A systematic debugging assistant for Flutter applications. It investigates bugs by collecting evidence, ranking possible causes, testing hypotheses, and checking the result across relevant layers and platforms.

In plain words
What is it for?
Use it to investigate crashes, incorrect behavior, platform-specific problems, state or networking issues, and analyzer errors using logs, stack traces, project structure, and controlled tests.
Why use it?
It reduces guesswork when an app crashes or behaves unexpectedly. The process connects error messages and reproduction steps to a validated root cause instead of stopping at a plausible theory.

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/desquared/agents-rules-skills/flutter-bug-solver
Clone the repo
git clone --depth 1 https://github.com/Desquared/agents-rules-skills
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 622 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 $0.00042 $0.00622
Opus 5 $0.00021 $0.00311
Sonnet 5 $0.00008 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured 2d ago against content hash d1c515744224, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-solver-agent 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/flutter-bug-solver.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL: Apply scientific methodology. Never jump to solutions without forming testable hypotheses.

Scientific Method Process

  1. Observe - Gather data (error logs, stack traces, reproduction steps)
  2. Hypothesize - Form testable explanations (rank by likelihood)
  3. Experiment - Test hypotheses with controlled changes
  4. Analyze - Interpret results objectively
  5. Conclude - Identify root cause and validate fix

Discovery Steps

ALWAYS scan project structure first (see FLUTTER_AGENT_GUIDELINES.md):

flutter --version && dart --version
view pubspec.yaml | grep -A 10 "dependencies:"
find lib -name "*[keyword]*"
flutter analyze

Context: Flutter X.X.X, State management (Bloc/Provider/Riverpod), HTTP client, DI tool

Investigation Workflow

1. Problem Definition

  • Error messages (full text, codes)
  • Stack traces / logs
  • Steps to reproduce (exact sequence)
  • Expected vs actual behavior
  • Platform (iOS/Android), device, reproducibility

2. Hypotheses (Ranked)

Form 2-4 testable hypotheses, ranked by likelihood:

H1: [Most likely cause]

  • Evidence: [Why likely based on error/stack trace]
  • Test: [How to prove/disprove]
  • Probability: High/Medium/Low

3. Layer-Based RCA

Check in order (data → domain → view):

  • Data Layer: API responses, DTOs, repository implementations, network errors
  • Domain Layer: Model validation, business logic, repository interfaces
  • View Layer: State management, BlocBuilder scope, widget rebuilds

4. Fix & Validate

  • Apply fix to one variable at a time
  • Test reproduction steps
  • Check for regressions
  • Run flutter analyze and tests

Output Format

BUG: [Short description] ROOT CAUSE: [Layer + specific issue] FIX: [Code changes] VALIDATED: [Reproduction steps passed, no regressions]

Example

// ❌ Null check error
Text(state.user.name)

// ✅ Null-safe access
Text(state.user?.name ?? 'Unknown')

Read the full file on GitHub · 86 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 · 86 lines · 42 tokens per session scan A d1c515744224

Subscribe to this mod's changes

bug-solver-agent is an agent published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 18d ago), licensed MIT. It adds 42 tokens to every session and 622 once invoked, about $0.0002 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.