track

track is a command for Claude Code from pleaseai/claude-code-plugins. It costs 14 tokens per session (416 once invoked), scanned A, original, MIT.

A command that registers existing Git branches with Graphite so it knows their parent branches. Graphite is a tool for managing dependent branch stacks.

In plain words
What is it for?
Use it to track the current or a named branch, track an external stack, or stop tracking a branch with the untrack option.
Why use it?
It brings branches created with ordinary Git commands or fetched from elsewhere under Graphite's tracking, so stack operations can work on them.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the graphite plugin — 3 skills, 16 commands shipped together

Good fit Use it to track the current or a named branch, track an external stack, or stop tracking a branch with the untrack option.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/pleaseai/claude-code-plugins/track
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/pleaseai/claude-code-plugins

Made for: Claude Code.

Or install graphite, the plugin that ships this one along with the rest of its 3 skills, 16 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

README.md
[![agentmods](https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/track/github.svg)](https://agentmods.dev/commands/pleaseai/claude-code-plugins/track)
Your own site
<a href="https://agentmods.dev/commands/pleaseai/claude-code-plugins/track"><img src="https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/track/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 track

Your own site · 80×15
<a href="https://agentmods.dev/commands/pleaseai/claude-code-plugins/track"><img src="https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/track.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 416 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00014 $0.00416
Opus 5 $0.00007 $0.00208
Sonnet 5 $0.00003 $0.00083
Haiku 4.5 $0.00001 $0.00042

Measured yesterday against content hash 85d9d5f70121, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

track 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 yesterday.

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.

plugins/graphite/commands/track.md · 34 lines

What it actually says

Bring branches that were created outside Graphite under gt's control by recording their parent. User input: $ARGUMENTS.

When you need this

  • The branch was created with raw git checkout -b and Graphite doesn't know its parent.
  • A teammate pushed branches you fetched via git fetch (not gt get).
  • gt metadata was corrupted and needs to be re-established.

Steps

  1. Run git branch --show-current to confirm the branch under cursor.
  2. If $ARGUMENTS starts with --untrack or is -u, run gt untrack <branch> and stop.
  3. Otherwise:
    • For the current branch: gt track (will prompt for parent if ambiguous).
    • For a specific branch: gt track <branch>.
    • To auto-pick the nearest ancestor as parent without prompting: gt track --force.
  4. To track an entire external stack, check out its tip and run gt track — it walks up until it hits an already-tracked branch.

Important warnings

  • Don't use raw git rebase on tracked branches afterwards — it can remove the base commit Graphite uses to identify the branch's start. If you must rebase, use gt modify --interactive or gt restack.
  • If gt track complains about diverged parent, run git rebase <parent> once to align the branch on its parent, then gt track again.

Key flags

  • -p, --parent <branch> — set parent explicitly (skip the prompt)
  • -f, --force — pick the nearest ancestor as parent automatically (useful for multi-branch tracking)
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. yesterday First seen · 34 lines · 14 tokens per session scan A 85d9d5f70121

Subscribe to this mod's changes

track is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 416 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-07.