init

A project-preparation workflow that interviews you about a project, investigates risks, and records its architecture, decisions, files, and known problems. It can start a new project or document an existing codebase.

In plain words
What is it for?
Use it to prepare a project, retrofit documentation onto a repository, create a development roadmap, and generate project guidance and registries.
Why use it?
It gives an agent a shared record of project boundaries and decisions before implementation, reducing missing context and repeated discovery work.

Skill for Claude CodeCodex

Part of the genesis plugin — 10 skills, 3 agents shipped together

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/godshiba/genesis/init
Any agent
npx skills add godshiba/genesis --skill init
Clone the repo
git clone --depth 1 https://github.com/godshiba/genesis

Made for: Claude Code, Codex.

Or install genesis, the plugin that ships this one along with the rest of its 10 skills, 3 agents.

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,671 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 $0.00109 $0.01671
Opus 5 $0.00055 $0.00835
Sonnet 5 $0.00022 $0.00334
Haiku 4.5 $0.00011 $0.00167

Measured 2d ago against content hash d5cbc1c75b1c, 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.

plugins/genesis/skills/init/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/genesis:init — The GENESIS Prep Protocol

Source of truth: the plugin's MASTER.md (doctrine) and templates/ (CLAUDE.template.md + registry skeletons). Both live at the plugin root — two directories above this skill's base directory, i.e. ../../MASTER.md and ../../templates/ from here. Read both before generating anything. Do not improvise structure that the templates already define.

The doctrine in one line: what isn't registered doesn't exist. The output of this skill is a project where that is mechanically true from day zero.

Mode Detection

Inspect the working directory first:

  • Greenfield (empty, or no source code): run all five steps below.
  • Existing repo: skip interview questions the repo already answers. Detect stack and commands from manifests (package.json, Package.swift, Cargo.toml, pyproject.toml, go.mod, Makefile), derive the dependency graph from imports, and mine git history plus existing docs for landmines and decisions already paid for. Read existing design specs by shape, not by origin — docs/specs/, adr/, rfc/, PRDs, design docs, or a tool's own spec folder (a generated *-design.md counts) — and lift each one's chosen approach and rejected alternatives into DECISIONS.md (citing the spec), its open questions into ISSUES.md, even when there are too few docs to trigger /genesis:docs. Then run only the steps with gaps (usually Interrogate's out-of-scope question and Phase). If the repo carries more than a handful of doc files, offer the /genesis:docs curation protocol as part of the retrofit — it inventories every doc, absorbs registry-shaped knowledge (decisions, gotchas, TODO lists) into the new registries, and reorganizes the rest behind an approval gate.
  • Already has a CLAUDE.md: do not overwrite. Read it, map its content onto the template slots, propose a migration diff, and get approval first.

Calibrating to the user

If the user seems new to Claude Code (asks what a step is for, or says so), briefly explain each step's purpose as you go and include the "Why these gates exist" pointer in the generated CLAUDE.md. If the user is clearly experienced, be terse: ask, decide, generate. Never skip steps in either mode — calibration changes narration, not rigor.

Read the full file on GitHub · 135 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.

  1. 2d ago First seen · 135 lines · 109 tokens per session scan A d5cbc1c75b1c

Subscribe to this mod's changes

init is a skill published in the GitHub repository godshiba/genesis (2 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 1,671 once invoked, about $0.0005 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.