new

new is a skill for Claude Code, Codex from vedantggwp/grimoire. It costs 103 tokens per session (2,973 once invoked), scanned A, original, MIT.

A setup guide for creating a Grimoire knowledge base, or project wiki. It checks the current folder for project files and uses what it finds to start the setup process.

In plain words
What is it for?
Use it to initialize a Grimoire, start a project wiki, or create a knowledge base from an existing code project.
Why use it?
It avoids making you begin a new knowledge base without context. It can distinguish an existing project from an empty or unrelated folder before asking setup questions.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the grimoire plugin — 8 skills 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/vedantggwp/grimoire/new
Any agent
npx skills add vedantggwp/grimoire --skill new
Clone the repo
git clone --depth 1 https://github.com/vedantggwp/grimoire

Made for: Claude Code, Codex.

Or install grimoire, the plugin that ships this one along with the rest of its 8 skills.

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.

agentmods badge for new

README.md
[![agentmods](https://agentmods.dev/badge/skills/vedantggwp/grimoire/new.svg)](https://agentmods.dev/skills/vedantggwp/grimoire/new)
Your own site
<a href="https://agentmods.dev/skills/vedantggwp/grimoire/new"><img src="https://agentmods.dev/badge/skills/vedantggwp/grimoire/new.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,973 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 $0.00103 $0.02973
Opus 5 $0.00051 $0.01486
Sonnet 5 $0.00021 $0.00595
Haiku 4.5 $0.00010 $0.00297

Measured 4d ago against content hash e2556b871385, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new 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 4d 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.

skills/new/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

new

Initialize a new Grimoire knowledge base. If run inside an existing project, intelligently discover context and pre-fill the questionnaire. Otherwise, run the full interactive flow.

Step 1 — Detect the Current Context

Before asking anything, look at the current working directory to understand what kind of environment Grimoire is being initialized in.

Check for project markers in the current directory:

Marker What it indicates
.git/ A git repository
package.json Node.js project
pyproject.toml, setup.py, requirements.txt Python project
Cargo.toml Rust project
go.mod Go project
Gemfile Ruby project
pom.xml, build.gradle Java project
README.md, README.rst Documented project
CLAUDE.md Claude Code project with existing instructions
docs/ directory Existing documentation

Determine the context:

  • Existing project — at least one project marker found
  • Empty directory — no markers, fresh start
  • Non-project directory — has files but no obvious project markers (e.g., Documents/Notes)

Step 2 — Offer the Onboarding Mode (CHECKPOINT)

Based on what was detected, present the user with a choice using AskUserQuestion.

If an existing project was detected

I see this is a {language} project ({project-name}). How would you like to start?

Options (use AskUserQuestion with these 4 options):

  1. Auto-discover context — "I'll read your README, CLAUDE.md, package.json, and docs/ to understand the project, then confirm each answer with you before scaffolding."
  2. Guided from scratch — "You answer all 7 questions manually. I won't peek at your project files."
  3. Hybrid — "I'll auto-discover, you review/edit each answer before I proceed."
  4. Tell me more first — "Show me what Grimoire does before I decide."

If the user picks option 4, briefly explain Grimoire's pipeline (scout → ingest → compile → present → serve) and re-ask.

Read the full file on GitHub · 315 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. 4d ago First seen · 315 lines · 103 tokens per session scan A e2556b871385

Subscribe to this mod's changes

new is a skill published in the GitHub repository vedantggwp/grimoire (2 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 2,973 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.

Related

Other skills, from other repositories