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/tdimino/claude-code-minoanWrote 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/tdimino/claude-code-minoan/claude-tracker)<a href="https://agentmods.dev/commands/tdimino/claude-code-minoan/claude-tracker"><img src="https://agentmods.dev/badge/commands/tdimino/claude-code-minoan/claude-tracker.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00257 |
| Opus 5 | $0.00000 | $0.00129 |
| Sonnet 5 | $0.00000 | $0.00051 |
| Haiku 4.5 | $0.00000 | $0.00026 |
Grade A, and why
claude-tracker 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 today.
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.
What it actually says
Claude Session Tracker
List recent Claude Code sessions with live status.
Usage:
/claude-tracker— recent sessions across all projects/claude-tracker --limit 5— fewer/claude-tracker --vscode— only projects open in a VS Code workspace
Arguments
$ARGUMENTS
Instructions
node ~/.claude/skills/claude-tracker-suite/scripts/list-sessions.js $ARGUMENTS
Each entry shows:
- LIVE badge with TTY (from Claude Code's own PID files, matched by session ID) or INACTIVE
- Name (the
-n/ auto name shown in the resume picker) and session summary - Session slug, project path, git remote and branch, repos touched
- Last user message time, session ID, keywords, last 3 user messages
To bring a session back: claude --resume <id|name> in the right directory, or ~/.claude/scripts/ghostty-resume.sh <id> for a new Ghostty tab. For crashed sessions use /claude-tracker-resume or claude-tracker-resume --open.
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.
- today Changed · -12 lines e2f5dd556a44
- 8d ago First seen · 39 lines · 0 tokens per session scan A 26f2c6074543
claude-tracker is a command published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 257 tokens. 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.
Other commands, from other repositories
gpd:settings
Configure autonomy, unattended execution budgets, runtime permission sync, workflow preset bundles, model-cost posture, runtime-specific tier model overrides, review cadence, and git preferences.
canvas
AI-orchestrated visual canvas production — create, populate, layout, present, generate, and export Obsidian canvases.
cmux
Manipulate the cmux terminal app via its CLI — save/restore workspace sessions to JSON, rename or close workspaces, and auto-assign workspace colors via a user-defined name→color rule file. Trigger phrases include "cmux", "save cmux", "restore cmux", "cmux workspaces", "color my cmux".
load
Resume from a saved session checkpoint. Reads a structured save state and produces a "Previously on..." briefing so you can pick up exactly where you left off.
enable-voice-alerts
Enable verbal notifications using macOS text-to-speech for Claude Code events.
ui-evidence
Discover, configure, and run ui-evidence for before/after UI review in this repo.