fight-repo-rot

fight-repo-rot is a skill for Claude Code from subinium/vibesubin. It costs 116 tokens per session (5,705 once invoked), scanned A, original, MIT.

A repository health check that finds dead code and other signs of codebase decay, then ranks the findings by confidence and importance.

In plain words
What is it for?
Use it before major features, refactoring, or open-sourcing to find unused code, oversized files, hardcoded paths, stale TODOs, and unusual import patterns.
Why use it?
It helps you decide what to clean up without immediately deleting or changing anything, reducing the risk of removing code that is still needed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/alice/Projects/foo.

Part of the vibesubin plugin — 12 skills, 1 hook shipped together

Good fit Use it before major features, refactoring, or open-sourcing to find unused code, oversized files, hardcoded paths, stale TODOs, and unusual import patterns.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add subinium/vibesubin
Claude Code
/plugin install vibesubin

Made for: Claude Code.

Or install vibesubin, the plugin that ships this one along with the rest of its 12 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fight-repo-rot

README.md
[![agentmods](https://agentmods.dev/badge/skills/subinium/vibesubin/fight-repo-rot/github.svg)](https://agentmods.dev/skills/subinium/vibesubin/fight-repo-rot)
Your own site
<a href="https://agentmods.dev/skills/subinium/vibesubin/fight-repo-rot"><img src="https://agentmods.dev/badge/skills/subinium/vibesubin/fight-repo-rot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fight-repo-rot

Your own site · 80×15
<a href="https://agentmods.dev/skills/subinium/vibesubin/fight-repo-rot"><img src="https://agentmods.dev/badge/skills/subinium/vibesubin/fight-repo-rot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,705 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00116 $0.05705
Opus 5 $0.00058 $0.02853
Sonnet 5 $0.00023 $0.01141
Haiku 4.5 $0.00012 $0.00571

Measured 13d ago against content hash 7264e6ea4d22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fight-repo-rot 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 13d 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.

plugins/vibesubin/skills/fight-repo-rot/SKILL.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fight-repo-rot

Repos don't break in a day. They rot over months as dead code accumulates, god files grow, hardcoded paths get committed, and six-month-old TODOs turn into forever-TODOs. This skill surfaces what's rotting — it never edits code.

What this skill is: a diagnosis, sorted by confidence and leverage, with a pointer to the skill that should handle each finding.

What this skill is not: an executor. It never deletes, refactors, rewrites, or runs tests. When the operator approves a finding, it hands off to another skill (refactor-verify for deletions and restructures, project-conventions for config fixes, audit-security for CVE dependency rot). This boundary is load-bearing — the moment this skill starts editing, the evidence chain breaks.

When to trigger

  • "find dead code" / "what can I delete"
  • "is any of this unused"
  • "clean up this repo" / "what's rotting"
  • "what should I clean up"
  • "where should I refactor"
  • "my repo is a mess"
  • "is my repo okay" (ambiguous — run this as a health check)
  • before a major new feature (survey the rot first)
  • before open-sourcing (don't surprise strangers)

State assumptions — before acting

Before starting the procedure, write an explicit Assumptions block. Don't pick silently between interpretations; surface the choice. If any assumption is wrong or ambiguous, pause and ask — do not proceed on a guess.

Required block:

Assumptions:
- Dispatch profile:  <static-strict (TypeScript strict, Rust) — HIGH confidence reachable | dynamic (Python, Ruby, loose JS) — default ceiling is MEDIUM>
- DI/reflection/codegen: <none detected | present — push all candidates down one tier>
- Test suite state:  <green (HIGH-confidence tags trustworthy) | red or missing (all tags downgraded one tier)>

Typical items for this skill:

  • Language's dynamic-dispatch profile (Python / Ruby / loose JS default to MEDIUM confidence even for apparent HIGH; Rust / TypeScript-strict can reach HIGH with static grep)
  • Whether reflection, DI containers, code generation, or dynamic imports are in play (every one of these pushes confidence down)
  • Whether the test suite runs to green — if no, HIGH-confidence dead-code tags are actually MEDIUM until tests are reliable

Read the full file on GitHub · 365 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. 13d ago First seen · 365 lines · 116 tokens per session scan A 7264e6ea4d22

Subscribe to this mod's changes

fight-repo-rot is a skill published in the GitHub repository subinium/vibesubin (50 stars, last pushed 4mo ago), licensed MIT. It adds 116 tokens to every session and 5,705 once invoked, about $0.0006 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 skills, from other repositories

neo-code-review

Use this skill when the user asks to review or audit source code, a PR, diff, commit, or recent changes for bugs, security, performance, tests, compatibility, or maintainability, duplicated code or logic across files, or hard-coded values. Also use it after an AI agent finishes modifying code to inspect the current…

Benknightdark/neo-skills · 87 tokens

neo-pr

Use this skill when the user asks to create, draft, review, format, or generate a Pull Request (PR) title and description, specify target or source branches for a repository, or convert git branch diffs into concise, high-impact, non-AI-slop PR content.

Benknightdark/neo-skills · 60 tokens

neo-rust

Use this skill when writing, refactoring, debugging, or auditing Rust code. Trigger for .rs files, Cargo projects, ownership/borrowing/lifetime issues, Result/Option error handling, unnecessary clone/performance work, unsafe code review, or modern Rust architecture.

Benknightdark/neo-skills · 58 tokens

coding-standards

Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.

gabrielrovesti/ai-agent-skills · 35 tokens

java-spring-code-review

Reviews Java and Spring Boot code changes with a findings-first workflow focused on behavioral regressions, contract drift, transaction and data-access risks, scheduler or async timing issues, security flaws, and performance problems. Use when the user asks to review code, inspect a PR or diff, check whether a backend…

gabrielrovesti/ai-agent-skills · 79 tokens

code-review-excellence

This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.

Galaxy-Dawn/claude-scholar · 43 tokens