A project-starting workflow that scans the whole codebase and its documentation before discussing requirements and creating project documents. It looks for architecture, testing, quality, bugs, missing information, and contradictions.

Use it when starting work on an existing or empty project, gathering requirements, documenting architecture, and recording software requirements.

It prevents planning from being based on assumptions or incomplete documentation. The initial scan gives the discussion a factual view of the existing project.

How MaximilianMayr94/skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to MaximilianMayr94/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/MaximilianMayr94/skills/main/.github/skills/init/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/MaximilianMayr94/skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/maximilianmayr94/skills/init.svg)](https://agentmods.dev/skills/maximilianmayr94/skills/init)

Your own site

<a href="https://agentmods.dev/skills/maximilianmayr94/skills/init"><img src="https://agentmods.dev/badge/skills/maximilianmayr94/skills/init.svg" alt="Measured on agentmods" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 392 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00024	$0.00392
Opus 5	$0.00012	$0.00196
Sonnet 5	$0.00005	$0.00078
Haiku 4.5	$0.00002	$0.00039

Measured 7d ago against content hash 64f6420822a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 7d 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.

.github/skills/init/SKILL.md · 27 lines

What it actually says

Phase 1 - Scan

Scan the whole project for existing documentation, architecture, code quality, test quality, bugs, gaps, problems and contradicting information. Use this as input for the interview and the generated documents. Do not assume that the existing information is correct. If the project is empty progress to phase 2 with the ``context.default.mdandsoftware_requirements.default.md` as input for the interview and generated documents.

Phase 2 - Discuss

Ask the user about:

project purpose, process, tech stack, quality and test expectations,
product scope, actors, user flows, detailed functionality, acceptance criteria and data contracts,
bugs, gaps, problems and contradictions in existing material.
Every few questions (max. 5) ask the user if he wants to progress to phase 3 or if he wants to continue refining with more questions.
For each question give the user a custom answer field so he can enter something else

Phase 3 - Create documents

Create copilot/context.md in the target project using context.default.md (this folder) as template.
Create copilot/software_requirements.md in the target project using software_requirements.default.md (this folder) as template.
Fill every section from interview answers and project scan.
Achieve a high-quality complete overview so architecture and implementation can be done without further questions. The better these documents are, the better architecture and implementation will be. Do not rush this step.
Reference content instead of copying it.

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.

7d ago First seen · 27 lines · 24 tokens per session scan A 64f6420822a5

Subscribe to this mod's changes

init is a skill published in the GitHub repository MaximilianMayr94/skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 392 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.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

skills: Skill for Claude Code