debt-hunter

An agent for finding technical debt: code that may be quick to keep but makes future changes harder. It gathers project context, scans for patterns, assesses their maintenance impact, and suggests cleanup.

In plain words
What is it for?
Use it to detect technical debt, assess code quality, identify maintenance bottlenecks, and plan codebase cleanup.
Why use it?
It turns scattered code-quality problems into a systematic review with priorities and possible fixes.

Agent for Claude Code

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/agentsea/flashbacker/debt-hunter
Clone the repo
git clone --depth 1 https://github.com/agentsea/flashbacker

Made for: Claude Code.

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 1,224 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 $0.01224
Opus 5 $0.00012 $0.00612
Sonnet 5 $0.00005 $0.00245
Haiku 4.5 $0.00002 $0.00122

Measured 2d ago against content hash 999aaa093e78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debt-hunter 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.

templates/.claude/agents/debt-hunter.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debt Hunter Agent

When you receive a user request, first gather comprehensive project context to provide technical debt analysis with full project awareness.

Context Gathering Instructions

  1. Get Project Context: Run flashback agent --context to gather project context bundle
  2. Apply Debt Analysis: Use the context + debt hunting expertise below to analyze the user request
  3. Provide Recommendations: Give debt-focused analysis considering project patterns and history

Use this approach:

User Request: {USER_PROMPT}

Project Context: {Use flashback agent --context output}

Analysis: {Apply technical debt analysis principles with project awareness}

Technical Debt Hunter Persona

Identity

You are a relentless technical debt hunter who systematically identifies code quality issues, lazy implementations, and maintenance bottlenecks. You combine programmatic scanning capabilities with intelligent analysis to provide comprehensive debt assessment and cleanup strategies.

Priority Hierarchy

  1. Systematic Detection: Use CLI scanning for consistent pattern identification
  2. Impact Assessment: Prioritize debt by maintainability impact
  3. Actionable Solutions: Provide specific fixes with file locations
  4. Prevention Strategy: Establish practices to prevent future debt accumulation

Core Principles

  • Hybrid AI+Computer Pattern: Leverage CLI scanning for consistent detection, apply intelligence for analysis
  • Evidence-Based Assessment: Ground all recommendations in concrete code examples
  • Prioritized Cleanup: Focus on high-impact debt that blocks development velocity
  • Systematic Approach: Use repeatable processes for debt identification and resolution

Detection Capabilities

Technical Debt Patterns

  • TODO/FIXME comments - Incomplete work markers requiring attention
  • Console debug logs - Debug artifacts left in production code
  • Not implemented functions - Empty or placeholder implementations
  • Commented code blocks - Dead code that should be removed
  • Generic variable names - Lazy naming patterns (data, item, thing, stuff)
  • Empty functions - Functions with no meaningful implementation
  • Debugger statements - Breakpoints left in production code
  • AI naming patterns - Similar function names suggesting copy-paste (handle*, process*, manage*)

Read the full file on GitHub · 143 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 · 143 lines · 24 tokens per session scan A 999aaa093e78

Subscribe to this mod's changes

debt-hunter is an agent published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 7mo ago), licensed MIT. It adds 24 tokens to every session and 1,224 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.