trekker:start

A command workflow for starting a Trekker task by changing its status to in progress. Trekker is the task-tracking system used by the project.

In plain words
What is it for?
Use it to search related tasks, inspect completed work, view task details and history, and then start a selected task.
Why use it?
It makes sure related past work and the task’s full history are reviewed before implementation begins. This reduces duplicated work and preserves useful context.

Command

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/obsfx/trekker-claude-code/start
Clone the repo
git clone --depth 1 https://github.com/obsfx/trekker-claude-code
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 441 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 $0.00009 $0.00441
Opus 5 $0.00005 $0.00220
Sonnet 5 $0.00002 $0.00088
Haiku 4.5 $0.00001 $0.00044

Measured 2d ago against content hash ea768af962a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trekker:start 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.

commands/start.md · 76 lines

What it actually says

Begin working on a task by setting its status to in_progress.

IMPORTANT: /trekker:start is a skill (invoke via Skill tool), NOT a bash command. There is no trekker start CLI command. Use trekker task update as shown below.

Arguments

  • $1: Task ID (e.g., TREK-1) - optional

If no task ID provided:

  1. Show current in_progress tasks
  2. Show ready tasks (todo status)
  3. Ask which task to start

Execution

Step 1: Search for Related Work (MANDATORY)

Before starting ANY task, search for related context:

# Search for related past work using keywords from the task
trekker search "<task title keywords>"
trekker search "<related concepts>"

# Check completed tasks that might inform this work
trekker --toon task list --status completed

Why search first:

  • Past tasks may contain solutions you need
  • Reveals related work and file locations
  • Prevents re-doing solved problems
  • Prefer continuity over re-implementation

Step 2: Gather Full Context via CLI (MANDATORY)

# Show task details
trekker task show <task-id>

# View change history for this task
trekker history --entity <task-id>

# Get comments for context
trekker comment list <task-id>

# Check dependencies
trekker dep list <task-id>

Why this matters:

  • Understand previous work on this task
  • See if it was started/stopped before
  • Recall decisions and blockers from past sessions
  • If context is unclear: STOP → SEARCH MORE → RESUME

Step 3: Start the Task

# Set status to in_progress
trekker task update <task-id> -s in_progress

After Starting

Display a summary including:

  • Task title and description
  • Key points from history/comments
  • Related tasks found via search
  • Any dependencies or blockers
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 · 76 lines · 9 tokens per session scan A ea768af962a5

Subscribe to this mod's changes

trekker:start is a command published in the GitHub repository obsfx/trekker-claude-code (4 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 441 once invoked, about $0.0000 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.