agentleFS
Sign inStart free
khendzelkhendzel/skills-janitor/skills/janitor-value/SKILL.md

janitor-value

Skill123 starsChanged 3 months agoMITView on GitHub

Show whether each skill is earning its context-window cost — combined tokens-used view sorted by waste. Use when the user asks 'are my skills worth it', 'what's my context budget', 'which skills are dead weight', or wants to audit skill value, token cost, or usage. Trigger with '/janitor-value'.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. juanmackie/juanskills★ 192% same

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 1 is distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read access to ~/.claude/skills, ~/.claude/agents, and local Claude Code session history

    line 32
  2. Distinctive:

    No authentication or API keys required — the script reads local files only

    line 33
  3. Very specific:

    If "unused skill cost" exceeds 20% of the budget, recommend the user run /janitor-report for a full health check or (in v1.4+) …

    line 53
  4. Very specific:

    Error: Every skill shows NO in the Used?

    line 75
  5. Very specific:

    Output: Run bash ~/.claude/skills/skills-janitor/scripts/value.sh, then present the table sorted by waste and the summary line, e.g.

    line 90
  6. Very specific:

    Output: Run bash ~/.claude/skills/skills-janitor/scripts/value.sh --weeks 12 --budget 500000 and present the same table with the adjusted …

    line 96
  7. Very specific:

    Output: Run the script with --json and return the JSON payload unmodified.

    line 102

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

  1. Error: value.sh: No such file or directory Solution: The plugin is installed under a different root. Locate it with ls ~/.claude/skills or check the plugin cache, then run the script from its actual location.
  2. Error: Every skill shows NO in the Used? column Solution: The lookback window may be too short or session history is empty. Re-run with a longer window, e.g. --weeks 12.
  3. Error: A skill shows 0 tokens Solution: Its SKILL.md is missing or unreadable. Run /janitor-report to surface broken skills, then /janitor-fix --prune to clean them up.
  4. Error: Percentages look wrong for a non-default model Solution: Pass the correct context size explicitly, e.g. --budget 500000.

Examples

Example 1: Standard value check

Input: "Are my skills worth their token cost?"

Output: Run bash ~/.claude/skills/skills-janitor/scripts/value.sh, then present the table sorted by waste and the summary line, e.g. "Always-loaded total: 8,420 tokens (4.2% of 200k budget). 6 of 31 skills unused in 4 weeks; top waster: heavy-skill (1,900 tokens, never used)."

Example 2: Longer lookback, custom budget

Input: "Check skill usage over the last quarter against a 500k window."

Output: Run bash ~/.claude/skills/skills-janitor/scripts/value.sh --weeks 12 --budget 500000 and present the same table with the adjusted lookback and percentages.

Example 3: Machine-readable output

Input: "Give me the raw skill value data."

Output: Run the script with --json and return the JSON payload unmodified.

MCP servers (v1.7)

For the MCP side of context cost, run bash {baseDir}/../../scripts/mcp.sh [--weeks N] — inventories every configured server (user, project, plugin) with REAL call counts from session transcripts, and lists servers unused in the window. No token guesses: schemas live server-side, so the janitor reports calls, distinct tools used, and last-used instead.

Resources

  • Report script (plugin-relative): {baseDir}/../../scripts/value.sh
  • /janitor-report — full health check including duplicates and broken skills
  • /janitor-fix --prune — remove broken symlinks and empty skill dirs
  • /janitor-discover — find new skills or check one before installing

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free