create-project

A setup tool for starting a new project inside an existing work area, using its source documents and any project starter files.

In plain words
What is it for?
Use it when creating a project from a brief, proposal, specification, or similar source inside an established work area.
Why use it?
It prevents new projects from being created as empty, generic folders with missing identity, principles, or structure.

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/andresanemic/lore-plugin/create-project
Any agent
npx skills add andresanemic/lore-plugin --skill create-project
Clone the repo
git clone --depth 1 https://github.com/andresanemic/lore-plugin

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,669 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 $0.00066 $0.03669
Opus 5 $0.00033 $0.01835
Sonnet 5 $0.00013 $0.00734
Haiku 4.5 $0.00007 $0.00367

Measured 2d ago against content hash 110acf54a856, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-project 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.

skills/create-project/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

create-project — Start a new project inside an area

New project, same domain. The standard has not changed, the anti-scope has not changed, the four things you always get wrong have not changed — and you are about to explain all of it again, because the folder is empty and empty folders know nothing.

They do not have to. This skill creates a concrete project inside an existing work area (made with create-area). The project inherits the area Lore and derives its folder structure and phases from its source documents (a spec PDF, a brief, a proposal), not from a fixed mold. If the area carries a project starter scaffold ({area}/_starter/, e.g. a Next.js template), the project is instantiated from it — this is how create-project replaces the old web-only nuevo-sitio without depending on any global starter folder.

Startup golden rule: the content of the project's identidad.md and principios.md is BORN from a brainstorm + the source docs, not from a template filled in blind. The template gives the shape; the brainstorm + the source give the content.

Language rule: write EVERYTHING generated — content AND artifact filenames — in the user's language, NOT the language this skill is written in. The names used throughout this skill (identidad.md, principios.md, FASES.md, proyectos/, fuente/) are the Spanish canonical forms: localize them (e.g. English → identity.md, principles.md, PHASES.md, projects/, source/). Fixed in every language: the area's selected contract name (CLAUDE.md or AGENTS.md), lore/, index.md, golden-paths.md, the <!-- lore:always-on --> marker pair (literal, never localized — localizing it breaks idempotent stamping silently). Consistency with the area wins: the project uses the area's actual folder and artifact names (its proyectos/-equivalent, its area-module filenames in inherited links); if the area's language differs from the user's, flag the mismatch and let the user pick. English terms of general technical use (workflow, stack, commit, scaffold…) stay in English.

Read the full file on GitHub · 263 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 · 263 lines · 66 tokens per session scan A 110acf54a856

Subscribe to this mod's changes

create-project is a skill published in the GitHub repository andresanemic/lore-plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 3,669 once invoked, about $0.0003 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

init

Initialize a personal Trove, a local file-based knowledge index for Claude Code. Use when the user says start/set up/create my trove, or when they want to remember things but no trove exists yet. Scaffolds the trove directory, INDEX.md and entries/ folder at user scope (/.claude/trove, follows you everywhere) or…

anishfyi/trove · 89 tokens

remember

Capture a durable learning into the personal Trove. Use when the user says remember this, note this, save to trove, add to my trove, or when a session surfaces a decision, gotcha, convention/preference, or external reference worth keeping. Writes one atomic entry file and updates INDEX.md.

anishfyi/trove · 65 tokens

index

Index the repository into Trove memory layers (symbols, modules, subsystems, architecture). Use when the user asks to index the repo, build the trove index, refresh symbols, or re-index after large changes.

anishfyi/trove · 46 tokens

query

Progressive retrieval from the Trove index. Use when the user asks what Trove knows about a subsystem, where code lives, or wants context assembled before editing. Runs architecture -> subsystem -> module -> symbol retrieval with a context budget.

anishfyi/trove · 49 tokens

context-ingest

The single entry point for getting anything new into your context architecture. Takes any input (documents, URLs, YouTube, meeting notes, pasted content) and triages it: dump to inbox, park in planned, or integrate into active docs. WHEN TO USE: "Here's a document — integrate it into my context" "Save this for later"…

walm00/business-context-os · 150 tokens

bcos-wiki

Wiki zone manager for BCOS — the universal long-form and cross-cutting content destination per plugin-storage-contract.md Rule 2. Stores runbooks, SOPs, decision logs, how-tos, glossaries, post-mortems, FAQs, meeting notes, and plugin cross-cutting context (charters, transcripts, research, customer-call notes). Two…

walm00/business-context-os · 154 tokens