agentic-skeleton-dir-structure

agentic-skeleton-dir-structure is a skill for Claude Code from psenger/ai-agent-skills. It costs 121 tokens per session (4,589 once invoked), scanned C, original, MIT.

A project scaffolding assistant for agentic AI codebases, including single repositories, monorepos, and projects using multiple programming languages. A monorepo is one repository containing several related projects; it uses a planning-first method called Spec-Driven Development.

In plain words
What is it for?
Use it to initialise or restructure agentic projects, gather requirements, create the planned folders and files, and show the resulting project tree.
Why use it?
It helps turn project requirements into a clear directory and file structure before implementation begins.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the psenger-skills plugin — 14 skills shipped together

Good fit Use it to initialise or restructure agentic projects, gather requirements, create the planned folders and files, and show the resulting project tree.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/psenger/ai-agent-skills/agentic-skeleton-dir-structure
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.

Any agent
npx skills add psenger/ai-agent-skills --skill agentic-skeleton-dir-structure
Clone the repo
git clone --depth 1 https://github.com/psenger/ai-agent-skills

Made for: Claude Code.

Or install psenger-skills, the plugin that ships this one along with the rest of its 14 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 agentic-skeleton-dir-structure

README.md
[![agentmods](https://agentmods.dev/badge/skills/psenger/ai-agent-skills/agentic-skeleton-dir-structure/github.svg)](https://agentmods.dev/skills/psenger/ai-agent-skills/agentic-skeleton-dir-structure)
Your own site
<a href="https://agentmods.dev/skills/psenger/ai-agent-skills/agentic-skeleton-dir-structure"><img src="https://agentmods.dev/badge/skills/psenger/ai-agent-skills/agentic-skeleton-dir-structure/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agentic-skeleton-dir-structure

Your own site · 80×15
<a href="https://agentmods.dev/skills/psenger/ai-agent-skills/agentic-skeleton-dir-structure"><img src="https://agentmods.dev/badge/skills/psenger/ai-agent-skills/agentic-skeleton-dir-structure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,589 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.04589
Opus 5 $0.00060 $0.02295
Sonnet 5 $0.00024 $0.00918
Haiku 4.5 $0.00012 $0.00459

Measured 9d ago against content hash 5ba16cea67c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

agentic-skeleton-dir-structure scanned grade C with 2 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 9d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

to the AI (e.g., "ignore previous instructions", shell metacharacters used as a value,

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

user to supply a valid one. Do not construct or run any command with an unvalidated value.
skills/agentic-skeleton-dir-structure/SKILL.md · 481 lines

How it starts

The opening of the file, as written. The whole thing — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Skeleton Directory Structure Skill v2.0

Scaffolds production-ready agentic AI project structures that integrate with Agent-OS v3 by Builder Methods.

This skill follows the Spec-Driven Development (SDD) methodology: ~95% planning, ~5% building. You shape detailed specifications before the AI writes any code.


When This Skill Activates

On activation, follow this sequence:

  1. Check for arguments. If $ARGUMENTS is provided, parse it for the repo pattern (single, mono, or multi-lang) and skip that question in Step 0.
  2. Detect the current directory. Run ls to check if the current directory already has files (existing project) or is empty/new. If existing:
    • Warn the user: "This directory already has files. I can scaffold around them or create a new subdirectory. Which do you prefer?"
    • If there is already a CLAUDE.md, ask if they want to overwrite or preserve it.
  3. Begin Step 0 — gather requirements through interactive questions.
  4. After all inputs are collected, present a summary and ask for confirmation before creating anything.
  5. Scaffold — create directories, generate files, show the final tree.
  6. Guide next steps — Agent-OS installation and SDD workflow.

Step 0 — Gather Requirements

Collect these six inputs. Ask one question at a time, wait for a response, then proceed to the next. Skip any question already answered via arguments or context.

Question 1 — Repo Pattern

What repo pattern do you want?

  • Single Repo — one app or service
  • Mono-Repo — multiple apps/services, same language ecosystem
  • Multi-Language Mono-Repo — services in different languages (e.g. Python + TypeScript + Go)

Question 2 — Platform Type

What type of project is this?

  • Frontend — SPA, SSR, static site
  • Backend — API, service, worker
  • Full-Stack — frontend + backend together
  • Middleware — gateway, BFF, proxy
  • Multi-Service — multiple independent services
  • Agents/AI — agentic AI service with tools, prompts, memory

Read the full file on GitHub · 481 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. 9d ago First seen · 481 lines · 121 tokens per session scan C 5ba16cea67c1

Subscribe to this mod's changes

agentic-skeleton-dir-structure is a skill published in the GitHub repository psenger/ai-agent-skills (10 stars, last pushed 3mo ago), licensed MIT. It adds 121 tokens to every session and 4,589 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (instruction-override phrasing, unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.