tax

tax is a command for Claude Code from AshtonYoon/claude-config-dashboard. It costs 61 tokens per session (310 once invoked), scanned B, original, MIT.

A command that reports how your Claude configuration is used, including measured token cost per session and installed items that were not used. Claude is a coding assistant, and its configuration can include plugins, agents, skills, hooks, and tool servers.

In plain words
What is it for?
Run it when you want a quick plain-text health check of your Claude setup. With the optional clean flag, it prints a review-first script that moves selected items to an archive instead of deleting them.
Why use it?
It shows which configuration items consume resources or sit idle, so you can review what may be worth keeping or cleaning up.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the claude-config-dashboard plugin — 2 commands shipped together

Good fit Run it when you want a quick plain-text health check of your Claude setup. With the optional clean flag, it prints a review-first script that moves selected items to an archive instead of deleting them.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ashtonyoon/claude-config-dashboard/tax
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.

Clone the repo
git clone --depth 1 https://github.com/AshtonYoon/claude-config-dashboard

Made for: Claude Code.

Or install claude-config-dashboard, the plugin that ships this one along with the rest of its 2 commands.

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 tax

README.md
[![agentmods](https://agentmods.dev/badge/commands/ashtonyoon/claude-config-dashboard/tax/github.svg)](https://agentmods.dev/commands/ashtonyoon/claude-config-dashboard/tax)
Your own site
<a href="https://agentmods.dev/commands/ashtonyoon/claude-config-dashboard/tax"><img src="https://agentmods.dev/badge/commands/ashtonyoon/claude-config-dashboard/tax/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 tax

Your own site · 80×15
<a href="https://agentmods.dev/commands/ashtonyoon/claude-config-dashboard/tax"><img src="https://agentmods.dev/badge/commands/ashtonyoon/claude-config-dashboard/tax.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 310 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00061 $0.00310
Opus 5 $0.00030 $0.00155
Sonnet 5 $0.00012 $0.00062
Haiku 4.5 $0.00006 $0.00031

Measured 9d ago against content hash c33b50451fc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

tax scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

command -v claude-config-dashboard || command -v uvx >/dev/null && echo "uvx claude-config-dashboard" || find "$HOME/.claude/plugins/cache/claude-config-dashboard" -name "dashboard.py" 2>/dev/null | sort -r | head -1
commands/tax.md · 26 lines

What it actually says

Run the Claude Config Dashboard's report mode and show the result directly.

Steps

  1. Pick a launcher, first available wins:

    command -v claude-config-dashboard || command -v uvx >/dev/null && echo "uvx claude-config-dashboard" || find "$HOME/.claude/plugins/cache/claude-config-dashboard" -name "dashboard.py" 2>/dev/null | sort -r | head -1
    
    • Installed console script: claude-config-dashboard
    • uvx (no install needed): uvx claude-config-dashboard
    • Plugin cache fallback: python3 "<found dashboard.py path>"
  2. Run it in report mode:

    <launcher> --report
    
  3. Show the report output to the user as-is — it's already plain text, no need to reformat or summarize it further.

  4. If the report's verdict mentions reclaimable tokens, tell the user they can run <launcher> --report --clean to also print a review-first archive script (mv-only, never deletes) that they can save and run themselves.

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. 9d ago First seen · 26 lines · 61 tokens per session scan B c33b50451fc8

Subscribe to this mod's changes

tax is a command published in the GitHub repository AshtonYoon/claude-config-dashboard (5 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 310 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.