track-start

track-start is a command for Claude Code from IvanLutsenko/awac-ai-agent-plugins. It costs 8 tokens per session (633 once invoked), scanned B, a copy of bug-close, MIT.

A command that starts recording activity for the current coding session in an Obsidian project. It stores the chosen project and session goal in a local tracking file.

In plain words
What is it for?
Use it when beginning focused work on a project so later actions can be saved as a session log.
Why use it?
It provides a record of what was done during a session and prevents two tracking sessions from being active at once.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the obsidian-tracker plugin — 19 skills, 19 commands shipped together

Good fit Use it when beginning focused work on a project so later actions can be saved as a session log.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add IvanLutsenko/awac-ai-agent-plugins
Claude Code
/plugin install obsidian-tracker

Made for: Claude Code.

Or install obsidian-tracker, the plugin that ships this one along with the rest of its 19 skills, 19 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 track-start

README.md
[![agentmods](https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/track-start.svg)](https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/track-start)
Your own site
<a href="https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/track-start"><img src="https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/track-start.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 633 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 86% copy Near-identical to another mod 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 $0.00008 $0.00633
Opus 5 $0.00004 $0.00316
Sonnet 5 $0.00002 $0.00127
Haiku 4.5 $0.00001 $0.00063

Measured 2d ago against content hash f01dadc6fcec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

track-start 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 2d 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.

cat .claude/obsidian-tracking.json 2>/dev/null || echo "NO_TRACKING"
Origin

This is a copy

86% identical to bug-close — 85 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/obsidian-tracker/commands/track-start.md · 68 lines

What it actually says

Track Start Command

Включает автоматический трекинг текущей сессии для логирования в Obsidian.

Step 0: Check Configuration

Вызови MCP tool:

mcp__plugin_obsidian_tracker_obsidian__getConfig

Если initialized: false: выполни инициализацию как в /projects команде.

Step 1: Check existing tracking

cat .claude/obsidian-tracking.json 2>/dev/null || echo "NO_TRACKING"

Если трекинг уже активен:

⚠️ Трекинг уже активен для проекта: {project}
Используй /track-stop чтобы завершить текущий.

Останови выполнение.

Step 2: Resolve project

Если project-name указан: используй его.

Если project-name НЕ указан:

  1. Получи список проектов:
    mcp__plugin_obsidian_tracker_obsidian__listProjects
    
  2. Спроси через AskUserQuestion какой проект трекать.

Step 3: Get goal

Спроси через AskUserQuestion:

  • "Какая цель этой сессии?" (текстовый ввод)

Step 4: Create tracking marker

Создай трекинг-файл через скрипт:

${CLAUDE_PLUGIN_ROOT}/scripts/start-tracking.sh "{project-name}" "{goal}"

Step 5: Confirm

🟢 Трекинг включён
- Проект: {project}
- Цель: {goal}
- Время: {started}

Твои действия будут автоматически записываться.
Используй /track-stop или /clear для сохранения в Obsidian.
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. 2d ago First seen · 68 lines · 8 tokens per session scan B f01dadc6fcec

Subscribe to this mod's changes

track-start is a command published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 8 tokens to every session and 633 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 86% identical to bug-close, differing in 85 lines, and is treated as a copy.