An initialization command for Shiplog, a project-tracking tool that records a project’s technology stack and feature work.

Use it to detect the stack, enter the project name and description, choose a feature-tracking mode, and initialize Shiplog.

It creates the project’s tracking configuration after checking whether Shiplog is already set up, so later tracking commands have the needed context.

init — Command by aadivar

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/aadivar/shiplog/init

Clone the repo

git clone --depth 1 https://github.com/aadivar/shiplog

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,293 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01293
Opus 5	$0.00000	$0.00647
Sonnet 5	$0.00000	$0.00259
Haiku 4.5	$0.00000	$0.00129

Measured 2d ago against content hash 650d49211dd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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/init.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/shiplog init

Initialize Shiplog project tracking on the current project.

Trigger

User runs /shiplog init

Behavior

Step 1: Check if already initialized

Check if .shiplog/config.json exists. If it does, inform the user:

"Shiplog is already initialized for this project. Run /shiplog config to modify settings."

Step 2: Detect project info

Run the stack detection script to auto-detect the tech stack:

bash scripts/detect-stack.sh

This returns a JSON array of detected technologies.

Step 3: Gather project info

Use the AskUserQuestion tool to collect project details. Ask these questions:

Question 1 — Project name & description:

Ask: "What's your project name and a brief description?"
If package.json, Cargo.toml, or similar exists, suggest the name from there

Question 2 — Tech stack:

Present the auto-detected stack and ask the user to confirm or modify
Options: Confirm detected stack / Modify

Question 3 — Tracking mode:

Ask: "How do you want to track features?"
Options:
- Vibe mode (Recommended) — Just build. Shiplog auto-discovers features from your commits and builds the PRD for you as you go. No upfront planning needed.
- Planned mode — Define features upfront in the PRD, then build. Shiplog tracks status as you work.

Question 4 — Agent model:

Ask: "Which model should background agents use?"
Options:
- haiku (Recommended) — Fastest and cheapest, great for append-only agent work
- sonnet — More capable, slightly higher cost
- opus — Most capable, highest cost

Question 5 — Background agents:

Ask: "Which background agents do you want to enable?"
Multi-select options (all enabled by default):
- Specs Agent — Logs architecture decisions automatically
- PRD Agent — Updates feature status from code changes
- Security Agent — Reviews for OWASP Top 10 after each task
- Memory Agent — Maintains code patterns and project memory

Step 4: Create directory structure

Create the following directories and files:

Read the full file on GitHub · 139 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.

2d ago First seen · 139 lines · 0 tokens per session scan A 650d49211dd7

Subscribe to this mod's changes

init is a command published in the GitHub repository aadivar/shiplog (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,293 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 2026-08-31.

Project management claude claude-code claude-code-plugin claude-skill

init

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/shiplog init

Trigger

Behavior

Step 1: Check if already initialized

Step 2: Detect project info

Step 3: Gather project info

Step 4: Create directory structure

What this file has done since we first saw it

Other commands, from other repositories

sm-sail

review

sm-barnacle

sm-scour

content-ideas

review-pr