shipkit-user-instructions

A task tracker for actions that the user must complete outside the coding agent. It stores these actions in a persistent JSON file so they remain available after the conversation.

In plain words
What is it for?
Use it to record and track tasks such as installing packages, adding API keys, running database migrations, configuring deployments, or setting up a Git repository.
Why use it?
It prevents manual steps, such as configuration or deployment work, from being forgotten in chat.

Skill for Claude CodeCodex

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 skills/stefan-stepzero/shipkit/shipkit-user-instructions
Any agent
npx skills add stefan-stepzero/shipkit --skill shipkit-user-instructions
Clone the repo
git clone --depth 1 https://github.com/stefan-stepzero/shipkit

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,213 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 $0.00038 $0.03213
Opus 5 $0.00019 $0.01606
Sonnet 5 $0.00008 $0.00643
Haiku 4.5 $0.00004 $0.00321

Measured 2d ago against content hash 89a924f8a34a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipkit-user-instructions 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.

install/skills/shipkit-user-instructions/SKILL.md · 397 lines

How it starts

The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipkit-user-instructions - Task Tracking for Manual User Actions

Purpose: Prevent manual tasks from being lost in chat by maintaining a persistent JSON tracking file for tasks that require user action outside Claude's control.

What it does: Captures manual tasks the user must complete, tracks their status, and persists them in .shipkit/user-tasks.json — a structured JSON artifact readable by Claude, machine-readable by other tools, and the single source of truth for user action items.

Output format: JSON — follows the Shipkit artifact convention for dashboard integration.


When to Invoke

Auto-trigger scenarios (other skills invoke this):

  • Package installation needed (implement)
  • External service configuration required (Lemon Squeezy webhooks, API keys)
  • Database migrations need running
  • Deploy configuration needed
  • Git repository setup required

Manual invocation:

  • User says: "Track this task", "Add to my todo", "Remind me to..."
  • Claude realizes: "I need the user to do X before I can continue"

Philosophy: If Claude can't do it directly, track it so it doesn't get forgotten.


Prerequisites

Optional:

  • .shipkit/ directory (will create if missing)

No hard prerequisites - This skill can run anytime.


Process

Step 1: Confirm Task Details

Before creating task entry, ask user 2-3 questions:

  1. What specific task needs to be done?

    • "Set up Lemon Squeezy webhook?"
    • "Configure webhook endpoint?"
    • "Set environment variable?"
    • (Let user describe or Claude infers from context)
  2. Why is this needed?

    • "For local webhook testing during development"
    • "To enable payment processing"
    • "To connect to production database"
  3. How urgent is this?

    • "Blocking me right now?" → High priority
    • "Needed before deploy?" → Medium priority
    • "Nice to have later?" → Low priority
  4. Which phase does this block? (infer from context when possible)

    • Read .shipkit/why.json to determine current stage (poc, mvp, growth, scale)
    • If the task is needed for the current stage → blocksPhase = current phase, blocking = true
    • If the task is needed for a future stage → blocksPhase = that future phase, blocking = false
    • If unclear or not phase-specific → blocksPhase = null, blocking based on priority

Read the full file on GitHub · 397 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 397 lines · 38 tokens per session scan A 89a924f8a34a

Subscribe to this mod's changes

shipkit-user-instructions is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 3,213 once invoked, about $0.0002 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.