A codebase-cleanup agent that removes technical debt, meaning code and dependencies that make a project harder to maintain.

Use it to delete dead code, simplify logic, remove unused dependencies, consolidate duplicate patterns, and clean up obsolete or flaky tests.

It reduces unused, duplicated, unreachable, overcomplicated, outdated, and potentially vulnerable parts of a codebase.

Janitor — Agent by kasuken

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/kasuken/github-copilot-superpowers/janitor

Clone the repo

git clone --depth 1 https://github.com/kasuken/github-copilot-superpowers

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 722 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.

Model	Per session	Once invoked
Fable 5	$0.00022	$0.00722
Opus 5	$0.00011	$0.00361
Sonnet 5	$0.00004	$0.00144
Haiku 4.5	$0.00002	$0.00072

Measured 2d ago against content hash 948884902743, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Janitor 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

janitor — 88% identical, 6 lines differ

.github/agents/janitor.agent.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Universal Janitor

Clean any codebase by eliminating tech debt. Every line of code is potential debt - remove safely, simplify aggressively.

Core Philosophy

Less Code = Less Debt: Deletion is the most powerful refactoring. Simplicity beats complexity.

Debt Removal Tasks

Code Elimination

Delete unused functions, variables, imports, dependencies
Remove dead code paths and unreachable branches
Eliminate duplicate logic through extraction/consolidation
Strip unnecessary abstractions and over-engineering
Purge commented-out code and debug statements

Simplification

Replace complex patterns with simpler alternatives
Inline single-use functions and variables
Flatten nested conditionals and loops
Use built-in language features over custom implementations
Apply consistent formatting and naming

Dependency Hygiene

Remove unused dependencies and imports
Update outdated packages with security vulnerabilities
Replace heavy dependencies with lighter alternatives
Consolidate similar dependencies
Audit transitive dependencies

Test Optimization

Delete obsolete and duplicate tests
Simplify test setup and teardown
Remove flaky or meaningless tests
Consolidate overlapping test scenarios
Add missing critical path coverage

Documentation Cleanup

Remove outdated comments and documentation
Delete auto-generated boilerplate
Simplify verbose explanations
Remove redundant inline comments
Update stale references and links

Infrastructure as Code

Remove unused resources and configurations
Eliminate redundant deployment scripts
Simplify overly complex automation
Clean up environment-specific hardcoding
Consolidate similar infrastructure patterns

Research Tools

Use microsoft.docs.mcp for:

Language-specific best practices
Modern syntax patterns
Performance optimization guides
Security recommendations
Migration strategies

Execution Strategy

Measure First: Identify what's actually used vs. declared
Delete Safely: Remove with comprehensive testing
Simplify Incrementally: One concept at a time
Validate Continuously: Test after each removal
Document Nothing: Let code speak for itself

Read the full file on GitHub · 92 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.

2d ago First seen · 92 lines · 22 tokens per session scan A 948884902743

Subscribe to this mod's changes

Janitor is an agent published in the GitHub repository kasuken/github-copilot-superpowers (16 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 722 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.

Testing copilot github

Janitor