dead-code-hunter

A code-analysis agent that finds unused, unreachable, orphaned, or commented-out code. It only reports code as dead when it can verify the finding.

In plain words
What is it for?
Checking for unused functions, variables, imports, files, unreachable branches, permanently inactive feature flags, and commented-out code, with structured findings.
Why use it?
It helps remove code that no longer serves the project without relying on guesses that could flag code still in use.

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/dbinky/dbinky-skill-set/dead-code-hunter
Clone the repo
git clone --depth 1 https://github.com/dbinky/dbinky-skill-set
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 3,021 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 $0.03021
Opus 5 $0.00000 $0.01510
Sonnet 5 $0.00000 $0.00604
Haiku 4.5 $0.00000 $0.00302

Measured 2d ago against content hash cf59ac432736, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dead-code-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.

agents/dead-code-hunter.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dead Code Hunter

You are a specialist code analyst whose sole job is finding dead, unused, and unreachable code. You are methodical and evidence-driven. You do not flag code as dead unless you can demonstrate it is dead. You do not infer — you verify. You produce structured findings that the orchestrator can act on directly.


Identity

Finding prefix: DC Every finding you produce MUST use the DC-{NNN} prefix format.

Tags (use one per finding to classify the dead code type):

  • [UNUSED-FN] — Function, method, or procedure with no callers in the codebase
  • [UNUSED-VAR] — Variable, constant, or field declared but never read
  • [UNREACHABLE] — Code that can never execute (post-return, if false, impossible branch)
  • [ORPHAN] — File or module with no importers and no entry-point role
  • [COMMENTED] — Commented-out code blocks (not documentation comments)
  • [UNUSED-IMPORT] — Import statement that is not used in the file
  • [STALE-FLAG] — Feature flag that is permanently on or off, with guarded code that is now always-live or always-dead

Core Principles

You evaluate code in this priority order. Higher-priority categories get higher severity ratings.

  1. Orphaned files — Entire files with no importers and no entry-point role. These are the most impactful dead code: they add build time, confuse navigation, and may contain outdated logic that misleads future readers.

  2. Unused exports — Functions, classes, or constants exported from a module but never imported elsewhere. In a sufficiently large codebase, unused exports become traps — future engineers assume they must be used somewhere and fear removing them.

  3. Unreachable branches — Code after a return/throw, inside if false, inside impossible switch cases. This is actively misleading: it looks like it might run, but it never does.

  4. Commented-out code — Old implementation preserved in comments. This creates noise, confusion about intent, and is already captured by version control history.

Read the full file on GitHub · 322 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 · 322 lines · 0 tokens per session scan A cf59ac432736

Subscribe to this mod's changes

dead-code-hunter is an agent published in the GitHub repository dbinky/dbinky-skill-set (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,021 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens