init

A session-initialization skill that examines a project or starts a structure for a new one. It can detect existing workflow folders and guide setup based on the kind of software being built.

In plain words
What is it for?
Use it to initialize project workflow files, choose a starter stack for a new web app, API, CLI, library, or full-stack project, and record the project’s name and purpose.
Why use it?
It prevents the first setup steps from being improvised and helps preserve or combine existing project instructions.

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/gh33k/session-plugin/init
Any agent
npx skills add gh33k/session-plugin --skill init
Clone the repo
git clone --depth 1 https://github.com/gh33k/session-plugin

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,574 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 $0.00030 $0.01574
Opus 5 $0.00015 $0.00787
Sonnet 5 $0.00006 $0.00315
Haiku 4.5 $0.00003 $0.00157

Measured yesterday against content hash 5495e732a01d, 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 yesterday.

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.

skills/init/SKILL.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

session:init

Initialize session workflow. For existing projects, analyzes codebase and pre-fills templates. For empty projects, asks what you're building and generates starter templates.

Instructions

1. Check Existing Structure

ls -d .project .beads .context 2>/dev/null

If .project/ exists, ask: Skip / Merge / Replace?

2. Detect Project State

ls -A | head -20

If empty or only has .git: → Go to Empty Project Flow If has files: → Go to Existing Project Flow


Empty Project Flow

E1. Ask What They're Building

New project detected. What are you building?

1. Web App (frontend with React/Vue/Next.js)
2. API/Backend (Node/Python/Go/Rust)
3. CLI Tool
4. Library/Package
5. Full-Stack (frontend + backend)
6. Other (describe it)

E2. Ask for Project Name and Description

What should we call this project? (short name)
Brief description? (1-2 sentences)

E3. Generate Starter Templates

Based on selection, create .project/ files with suggested stack:

Type Suggested Stack
Web App TypeScript, React/Next.js, Tailwind, Vitest
API/Backend TypeScript/Python, Express/FastAPI, Jest/Pytest
CLI Tool TypeScript/Rust, Commander/Clap
Library TypeScript, Vitest, tsup for bundling
Full-Stack TypeScript, Next.js or separate frontend/backend

Create directories and templates (see Create Directories and templates below).

E4. Report and Suggest Plan Session

Project initialized: {name}

Created .project/ with starter templates for {type}.
Stack suggestion: {suggested stack}

Next step: /session:start plan

In the plan session, you'll:
- Refine the project scope and architecture
- Define principles and constraints
- Break down into initial tasks
- Set your first focus area

Stop here for empty projects.


Existing Project Flow

3. Analyze Codebase

Read the full file on GitHub · 305 lines

Files

What ships with it

5 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. yesterday First seen · 305 lines · 30 tokens per session scan A 5495e732a01d

Subscribe to this mod's changes

init is a skill published in the GitHub repository gh33k/session-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 30 tokens to every session and 1,574 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.