shipkit-project-context

A project-scanning guide that detects a project’s programming stack, environment requirements, and database structure from its files, then records the results in structured context files.

In plain words
What is it for?
Use it when starting a project or refreshing its context to generate .shipkit/stack.json and, when possible, environment and database-schema information.
Why use it?
It gives other development tools a current, shared description of the project instead of making them infer the stack from scratch. It can also avoid unnecessary rescans when files have not changed.

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-project-context
Any agent
npx skills add stefan-stepzero/shipkit --skill shipkit-project-context
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 5,551 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 $0.05551
Opus 5 $0.00019 $0.02776
Sonnet 5 $0.00008 $0.01110
Haiku 4.5 $0.00004 $0.00555

Measured 2d ago against content hash b886d0b4d7ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipkit-project-context 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-project-context/SKILL.md · 575 lines

How it starts

The opening of the file, as written. The whole thing — 575 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipkit-project-context - Smart Project Context Scanner

Purpose: Generate and maintain lightweight project context files (stack, env, schema) by scanning package files, configs, and migrations. Uses file modification time checks to avoid unnecessary rescans.

What it does: Scans project files to detect tech stack, environment requirements, and database schema. Generates .shipkit/stack.json as a structured JSON artifact, plus optional markdown files for env and schema.

Output format: JSON — readable by Claude, machine-readable by other tools, and the single source of truth for project tech stack.


When to Invoke

User triggers:

  • "Scan the project"
  • "Update context"
  • "Rescan stack"
  • "Generate project context"
  • "What's my tech stack?"

Auto-triggered by:

  • session start / any skill needing stack.json (when it is missing or stale)

First run:

  • No .shipkit/ directory exists
  • User starts new Shipkit project

Prerequisites

Required:

  • Project has package.json (or equivalent dependency file)

Optional but helpful:

  • .env.example (for env requirements)
  • Database migration files (for schema)
  • Config files (next.config.js, tailwind.config.js, etc.)

Process

Completion Tracking

This skill produces 3 files, not 1. Create tasks:

  • TaskCreate: "Write stack.json"
  • TaskCreate: "Write env-requirements.md"
  • TaskCreate: "Write schema.json"
  • TaskCreate: "Detect working patterns (Step 3.5)"

TaskUpdate each task to in_progress when starting it, completed when done.

stack.json alone is NOT done — env-requirements.md and schema.json must also be written. Do NOT present the completion summary until all 3 files exist.

Step 1: Check Freshness (Smart Caching)

Before doing any work, check if rescan is needed.

Commands: See references/bash-commands.md for platform-specific freshness checks

Freshness logic:

  1. If .shipkit/stack.json doesn't exist → First run, proceed directly to Step 3 (scan).
  2. If stack.json exists:
    • Compare modification times.
    • If stack.json newer than package.jsonSKIP SCAN, read cached file and exit early with a "using cached stack" report.
    • If package.json newer than stack.json → Rescan automatically (no prompt). Archive the stale stack.json if overwrite risk matters, then proceed to Step 3.

Read the full file on GitHub · 575 lines

Files

What ships with it

3 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 · 575 lines · 38 tokens per session scan A b886d0b4d7ec

Subscribe to this mod's changes

shipkit-project-context 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 5,551 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.