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.
git clone --depth 1 https://github.com/AshtonYoon/claude-config-dashboardWrote 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.
[](https://agentmods.dev/commands/ashtonyoon/claude-config-dashboard/tax)<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.
<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>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 5.1 | $0.00061 | $0.00310 |
| Opus 5 | $0.00030 | $0.00155 |
| Sonnet 5 | $0.00012 | $0.00062 |
| Haiku 4.5 | $0.00006 | $0.00031 |
Grade B, and why
tax scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
command -v claude-config-dashboard || command -v uvx >/dev/null && echo "uvx claude-config-dashboard" || find "$HOME/.claude/plugins/cache/claude-config-dashboard" -name "dashboard.py" 2>/dev/null | sort -r | head -1 What it actually says
Run the Claude Config Dashboard's report mode and show the result directly.
Steps
-
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>"
- Installed console script:
-
Run it in report mode:
<launcher> --report -
Show the report output to the user as-is — it's already plain text, no need to reformat or summarize it further.
-
If the report's verdict mentions reclaimable tokens, tell the user they can run
<launcher> --report --cleanto also print a review-first archive script (mv-only, never deletes) that they can save and run themselves.
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.
- 9d ago First seen · 26 lines · 61 tokens per session scan B c33b50451fc8
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.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
adr-supersede
Create a new ADR that supersedes an existing one.