Audit, clean and swipe-triage your Claude Code skills — honest always-loaded vs on-demand token costs, usage tracking, duplicate detection, and safe deletion (auto-fix, prune, interactive swipe TUI)

MIT License

Installation

Open Claude Code and run this command:

/plugin install skills-janitor@claude-code-plugins-plus

Use --global to install for all projects, or --project for current project only.

What It Does

> Tinder for your Claude Code skills. Swipe through your collection and delete what's wasting context, in seconds.

Works with Claude Code and OpenAI Codex. 5 commands, zero dependencies.

!/janitor-swipe — swipe keep / delete / skip through every installed skill

> New in v1.4: /janitor-swipe. Every installed skill becomes a card, sorted heaviest-and-least-used first. Swipe left to delete, right to keep, down to skip. Most setups clear 30–40% of their skill token cost before the deck even ends. Jump to swipe →

Scans every place a skill lives: user, project, codex, and every skill installed via /plugin install. Surfaces duplicates, broken symlinks, and unused skills cluttering your context.

Skills (5)

janitor-discover View full skill →

"Find new skills on GitHub or check a specific skill before installing.

ReadBash(bash:*)

Skill Discovery & Pre-Install Check

Combined entry point for finding skills on GitHub and for evaluating a specific skill (URL or local path) before installing it.

Overview

Replaces the v1.2 split between /janitor-search and /janitor-precheck. The dispatcher picks the right mode from the argument shape. Search results are relevance-gated (a repo must carry a skill signal in its name/description/topics) and ranked by relevance before stars, so generic mega-repos don't crowd out actual skills.

Argument	Mode	What runs
Keyword(s) like `seo` or `n8n workflows`	Discovery	`search.sh` — find matching skills on GitHub
`--compare`	Comparison	`search.sh --compare` — find alternatives to a local skill
Full URL: `https://github.com/user/skill`	Pre-install check	`precheck.sh` — analyze before installing
Short repo: `user/skill`	Pre-install check	`precheck.sh` (auto-expanded to URL)
Local path: `~/path/to/skill`	Pre-install check	`precheck.sh` (local folder)

Prerequisites

Claude Code with the skills-janitor plugin installed (provides scripts/discover.sh, search.sh, precheck.sh, compare.sh)
bash 3.2+ and curl
Network access to api.github.com (anonymous OK; set GITHUB_TOKEN for higher rate limits and code search)

Instructions

Step 1: Dispatch on argument shape


bash ~/.claude/skills/skills-janitor/scripts/discover.sh <query-or-url> [options]

Examples:

discover.sh seo — search for SEO-related skills
discover.sh n8n --limit 20 — top 20 n8n skills
discover.sh --compare marketing-seo-audit — alternatives to a local skill
discover.sh https://github.com/user/my-skill — check before installing
discover.sh user/my-skill — same, short form

Step 2: Present results per mode

Discovery mode — ranked list of GitHub repos with skill name, description, stars, last updated, and a one-line verdict.

Pre-install mode — overlap analysis: which of the user's existing skills (including plugin skills) overlap with the candidate by description, and a recommendation to install / skip / replace.

Output

Discovery: a numbered table (repository, stars, updated, INSTALLED/AVAILABLE status). Pre-install: overlap buckets (HIGH ≥60%, MODERATE 30–

janitor-fix View full skill →

"Automatically fix skill problems (safe preview first).

ReadBash(bash:*)

Auto-Fix

Automatically fix common skill issues. Dry-run by default — shows what would change without modifying files.

Overview

Repairs frontmatter problems (missing delimiters, empty descriptions, missing version fields) across user, project, and codex-scope skills, and — in --prune mode — removes broken symlinks and empty skill directories. Plugin/marketplace skills are never modified (changes would be overwritten on update).

Prerequisites

Claude Code with the skills-janitor plugin installed (provides scripts/fix.sh)
bash 3.2+ (the stock macOS bash works; no external dependencies)
Write access to the user's own skill directories (~/.claude/skills, ./.claude/skills, ~/.agents/skills)

Instructions

Step 1: Preview first (always)


bash ~/.claude/skills/skills-janitor/scripts/fix.sh            # preview fixes
bash ~/.claude/skills/skills-janitor/scripts/fix.sh --prune    # preview broken/orphaned removals

Step 2: Show the user the preview and confirm

Never jump straight to --apply. Present the [DRY RUN] lines and ask before writing.

Step 3: Apply


bash ~/.claude/skills/skills-janitor/scripts/fix.sh --apply           # apply fixes
bash ~/.claude/skills/skills-janitor/scripts/fix.sh --prune --apply   # remove broken skills

What it fixes:

Adds missing frontmatter delimiters (---)
Fills empty description fields with a template
Adds missing version field (defaults to "1.0.0")
Generates template descriptions using the skill folder name

Prune mode finds and removes:

Broken symlinks — skill folder points to deleted source
Empty directories — skill folder with no SKILL.md
Orphaned skills — user-scope copies of plugin skills

Safety model: dry-run by default (must pass --apply to write), skips plugin/marketplace skills, logs ALL changes with timestamps to data/changelog.log, always asks for confirmation before removing.

Output

Per-skill action lines ([DRY RUN] / [FIXED] / [PRUNED] / [SKIP]) followed by a summary of fixable issues, skipped items, and prunable entries. In dry-run mode the summary ends with "Run with --apply to make these changes."

Error Handling

Error: A fix produced an unexpected result in a SKILL.md

Solution: Every applied change is logged in data/changelog.log with a timestamp — show the log entry and restore the affected field manually; template descriptions are meant to be replaced by the

janitor-report View full skill →

"Full health check of all your skills in one report.

ReadBash(bash:*)

Health Report

Generate a comprehensive health report combining inventory, quality checks, duplicate detection, and broken skill findings.

Overview

One report covering every place a skill lives: user, project, codex, plugin, and source scopes. Plugin skills appear with their full invocation name (e.g. marketing-skills:image, figma:figma-use) — these were invisible to the v1.2 report. The scan JSON also includes an agents array (subagents from ~/.claude/agents — their descriptions are always-loaded too) and per-plugin update_available (installed commit vs marketplace HEAD) — surface stale plugins and heavy agents in the report.

Modes:

/janitor-report (default) — full health check: inventory + lint + duplicates + broken
/janitor-report --brief — inventory only (replaces the old /janitor-audit)

Prerequisites

Claude Code with the skills-janitor plugin installed (provides scripts/scan.sh, lint.sh, detect_dupes.sh)
bash 3.2+ (the stock macOS bash works; no external dependencies)
Read access to ~/.claude/skills, ~/.claude/agents, and installed plugin metadata
No authentication or API keys required — the scripts read local files only

Instructions

Step 1: Run the scripts

Full report:


bash ~/.claude/skills/skills-janitor/scripts/scan.sh
bash ~/.claude/skills/skills-janitor/scripts/lint.sh
bash ~/.claude/skills/skills-janitor/scripts/detect_dupes.sh

Brief mode (inventory only):


bash ~/.claude/skills/skills-janitor/scripts/scan.sh

Step 2: What each script covers

Inventory (scan.sh) — all skills across scopes, symlink status, frontmatter fields, line counts; agents and plugins (with updateavailable) arrays; brokensymlinks count.
Quality checks (lint.sh) — Critical: broken symlinks, missing SKILL.md, missing frontmatter. Warning: missing/empty name or description, description too short/long, missing version. Info: no body content, no Gotchas section, large files.
Duplicate detection (detect_dupes.sh) — name collisions (two distinct skills with the same qualified name at different paths) and description overlap (Jaccard similarity >30%), with cross-scope user-vs-plugin pairs explicitly surfaced (e.g. marketing-seo-audit (user) ↔ marketing-skills:seo-audit (plugin)).

Step 3: Present a unified report

Merge the three outputs into one table with severity levels, then recommend actions.

Output


| Skill


                
                  
                  janitor-swipe
                  View full skill →
                
                
                  "Tinder for your Claude Code skills.
                  
                      ReadBash(bash:*)
                    
                
                
                  Janitor Swipe — interactive skill triage
A bash TUI that puts every installed skill into a sorted deck and lets the user swipe keep / delete / skip on each card.
Overview
The deck is sorted "most likely waste first" — heavy, never-used skills appear at the top, so most users hit ← delete a few times and quit before reviewing the whole list. The swipe is scope-aware and honest about what it can delete: user-scope skills are actually removed (after confirmation), plugin skills are flagged for review instead.
Prerequisites

Claude Code with the skills-janitor plugin installed (provides scripts/swipe.sh and swipe-build-deck.sh)
bash 3.2+ (the stock macOS bash works; no external dependencies)
An interactive terminal at least 50 columns x 22 rows — the TUI reads single keypresses

Instructions
Step 1: Tell the user to run it via !
Inside Claude Code, the Bash tool's stdin is non-interactive, so the keypress reader can't work. The user must invoke it via the ! prefix so the command runs in their actual shell:

!bash ~/.claude/skills/skills-janitor/scripts/swipe.sh

When the user asks for /janitor-swipe, tell them to run that command in their terminal. Do NOT try to run it yourself via the Bash tool — it will error with "needs an interactive terminal".
Step 2: Explain the card and controls
Each card shows:

Skill name + position in deck (e.g. [3 / 47])
Context cost split: X always · Y on trigger (description tokens are permanent; body loads only when the skill fires)
Usage count and last invoked date
Scope (user, project, plugin · , etc.)
3-line truncated description
Verdict label (e.g. "Unused + heavy on trigger — prime delete candidate")

Controls:

← / h / d — stage for delete
→ / l / k — keep
↓ / j / s / space — skip
u — undo (back up one card, clear its decision)
i — inspect (show full SKILL.md description)
q / Esc — quit (still shows summary for decisions made so far)

Step 3: Scope-aware deletion (the critical correctness point)

Scope
What happens on swipe left


user, project, codex-user, codex-project
Path is staged for rm -rf (or unlink if symlink)


plugin, plugin-source
NOT deleted — flagged under "Plugins to review" at the apply screen,
                
              
                
                  
                  janitor-value
                  View full skill →
                
                
                  "Show whether each skill is earning its context-window cost — combined tokens-used view sorted by waste.
                  
                      ReadBash(bash:*)
                    
                
                
                  Skill Value Report
Show whether each installed skill is earning the context-window tokens it costs.
Overview
Combine token cost and usage tracking into a single view of every installed skill, sorted with the heaviest unused skills at the top. The report splits each skill's cost into what is permanently loaded (the description) and what only loads on demand (the body), then cross-references recent invocations so the user can see which skills are dead weight.
Replaces the v1.2 split between /janitor-tokens (cost only) and /janitor-usage (usage only).
Prerequisites

Claude Code with the skills-janitor plugin installed (provides scripts/value.sh)
bash 3.2+ (the stock macOS bash works; no external dependencies)
Read access to ~/.claude/skills, ~/.claude/agents, and local Claude Code session history
No authentication or API keys required — the script reads local files only

Instructions
Step 1: Run the value script

bash ~/.claude/skills/skills-janitor/scripts/value.sh [--weeks N] [--budget N] [--json]


--weeks N — usage lookback window (default: 4)
--budget N — context window size for % calculations (default: 200000)
--json — emit raw JSON

Step 2: Present the results
Show the table and summary to the user. When explaining results, do NOT describe body tokens as permanent context cost — only descriptions are always loaded. Plugin-namespaced skills appear with their full invocation name (e.g., marketing-skills:image, figma:figma-use).
Step 3: Suggest action when waste is high
If "unused skill cost" exceeds 20% of the budget, recommend the user run /janitor-report for a full health check or (in v1.4+) /janitor-swipe to triage interactively.
Output
A table of every installed skill with:

Always — description tokens, permanently in the system prompt (the real context rent)
Body — the rest of SKILL.md, loaded only when the skill triggers (progressive disclosure)
Used? — yes if invoked in the lookback window, else NO
Last Used — date of most recent invocation

Followed by a summary:

Total tokens loaded into context (the always-loaded TOTAL includes skills plus subagent descriptions from ~/.claude/agents, reported as % of budget)
Active vs. unused split
Top wasters: heavy skills with zero usage

Error Handling

Error: value.sh: No such file or directory

Solution: The plugin is installed under a different
                
              
          
        

      
      

      
      

      
      

      
      
  Ready to use skills-janitor?
  
    
    
        
        View on GitHub
      
  




      
      
          Related Plugins
          
            
  fairdb-ops-manager
  Database operations management for FairDB PostgreSQL clusters
  /plugin install fairdb-ops-manager@claude-code-plugins-plus
  

  jeremy-firestore
  Firestore database specialist for schema design, queries, and real-time sync
  /plugin install jeremy-firestore@claude-code-plugins-plus
  

  claude-never-forgets
  Persistent memory plugin for Claude Code - remembers preferences, decisions, and corrections across sessions and context limits
  /plugin install claude-never-forgets@claude-code-plugins-plus
  

  geepers-agents
  Multi-agent orchestration system with 51 specialized agents for development workflows, code quality, deployment, research, games, and more. Includes orchestrators for checkpoint, deploy, quality, fullstack, research, games, corpus, web, and python workflows.
  /plugin install geepers-agents@claude-code-plugins-plus
  

  sprint
  Autonomous multi-agent development framework with spec-driven sprints. Write specs, run /sprint, and let coordinated agents (backend, frontend, QA, UI testing) handle implementation through self-iterating convergent loops.
  /plugin install sprint@claude-code-plugins-plus
  

  geepers-agents
  Multi-agent orchestration system with 51 specialized agents for development workflows, code quality, deployment, research, and more. Built with MCP tools and Claude Code plugin agents.
  /plugin install geepers-agents@claude-code-plugins-plus
  

          
        

      
      
          Tags
          
            skillscleanupcontext-windowtoken-budgetmaintenancetui
          
        
    
  

  

    

    
    
        
            
                Agent Skills in Your Inbox
                
                    
                    
                    
                
                No spam, ever. Unsubscribe with one click.
            

            
                
                    Product
                    
                        Explore
                        Skills
                        Cowork
                        Compare
                        Tools
                    
                
                
                    Resources
                    
                        Docs
                        Changelog
                        Collections
                        Playbooks
                        Research
                        Learning
                    
                
                
                    Company
                    
                        Community
                        Hall of Fame
                        GitHub
                    
                
                
                    Legal
                    
                        Privacy
                        Terms
                        Acceptable Use
                    
                
            

            
                Tons of Skills by Intent Solutions. Marine. Citadel Grad. 20 years ops → self-taught dev → AI architect.
                © 2026 Tons of Skills | Intent Solutions