track

A command that writes structured events to a feature's JSON Lines progress log. JSON Lines is a text format where each line contains one JSON record.

In plain words
What is it for?
Use it to record task starts and completions, affected files, errors, blockers, session boundaries, and passed or failed quality checks.
Why use it?
It creates a consistent history of checkpoints, task changes, errors, blockers, and quality checks instead of leaving progress scattered across notes.

Command for Claude Code

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.

agentmods
npx agentmods add commands/parkerm2/create-claude-workflow/track
Clone the repo
git clone --depth 1 https://github.com/ParkerM2/create-claude-workflow

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,039 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.01039
Opus 5 $0.00013 $0.00519
Sonnet 5 $0.00005 $0.00208
Haiku 4.5 $0.00003 $0.00104

Measured 2d ago against content hash 870f1131cb3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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.

.claude/commands/track.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/track — Emit a Tracking Event

Emit a structured event to the feature's JSONL progress log. Feature is auto-detected from the current git branch.


Usage

/track <event-type> <message> [--files f1,f2] [--task N]

Examples

/track checkpoint "pre-merge-wave-2"
/track task.started "Implementing auth service" --task 2
/track task.completed "Auth service complete" --files src/auth.ts,src/types.ts --task 2
/track error.encountered "Type mismatch in src/service.ts:42"
/track blocker.reported "Cannot resolve circular dependency in auth module"
/track qa.passed "Task #3, round 1, all criteria met" --task 3
/track qa.failed "Task #3, round 1, missing error handling" --task 3
/track warning.logged "Large file detected: src/utils.ts exceeds 500 lines"
/track session.start "Starting feature implementation"
/track session.end "Feature complete"

Phase 1: Parse Input

Extract from the user's input:

  • event-type: The dot-namespaced event type (e.g., checkpoint, task.completed)
  • message: The descriptive message (everything after event-type, before flags)
  • --files: Optional comma-separated list of file paths
  • --task: Optional task number

Phase 2: Detect Feature

Auto-detect the feature from the current git branch:

git branch --show-current

Parse the branch name:

  • work/<feature>/<task> → feature = <feature>
  • feature/<feature> → feature = <feature>
  • hotfix/<name> → feature = <name>
  • refactor/<name> → feature = <name>
  • Other → warn user, ask for feature name

Phase 3: Build Event Data

Map the event-type to a data payload:

Event Type Data Fields
session.start { command: "track", feature, branch, mode: null }
session.end { reason: message, duration_s: null, tasks_completed: null }
checkpoint { label: message, branch, plan_step: null, resumable: true }
task.started { taskId: --task, summary: message, agent: null, files: --files }
task.completed { taskId: --task, summary: message, files_changed: --files }
task.failed { taskId: --task, error: message, attempts: null }
qa.started { taskId: --task, round: null, reviewer: null }
qa.passed { taskId: --task, round: null, summary: message }
qa.failed { taskId: --task, round: null, issues: [message] }
error.encountered { file: null, line: null, error: message, attempts: null, resolved: false }
blocker.reported { description: message, agent: null, task: --task }
warning.logged { message: message, context: null }

Read the full file on GitHub · 114 lines

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 · 114 lines · 26 tokens per session scan A 870f1131cb3c

Subscribe to this mod's changes

track is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,039 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 2026-08-31.