init-deep

init-deep is a skill for Claude Code from ils15/pantheon-legacy. It costs 21 tokens per session (913 once invoked), scanned A, original, MIT.

A workflow that generates AGENTS.md instruction files throughout a project directory tree. Each file gives coding agents context specific to that directory, such as its purpose, conventions, and testing practices.

In plain words
What is it for?
Use it to create hierarchical guidance for source code, routes, models, tests, migrations, and other folders, with a configurable maximum directory depth.
Why use it?
It keeps instructions close to the files they describe. Agents can then apply project-wide rules and more specific directory rules without relying on one large, general document.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: mentions AGENTS.md.

Good fit Use it to create hierarchical guidance for source code, routes, models, tests…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ils15/pantheon-legacy/init-deep
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 ils15/pantheon-legacy --skill init-deep
Clone the repo
git clone --depth 1 https://github.com/ils15/pantheon-legacy

Made for: Claude Code.

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 init-deep

README.md
[![agentmods](https://agentmods.dev/badge/skills/ils15/pantheon-legacy/init-deep.svg)](https://agentmods.dev/skills/ils15/pantheon-legacy/init-deep)
Your own site
<a href="https://agentmods.dev/skills/ils15/pantheon-legacy/init-deep"><img src="https://agentmods.dev/badge/skills/ils15/pantheon-legacy/init-deep.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 913 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00021 $0.00913
Opus 5 $0.00010 $0.00456
Sonnet 5 $0.00004 $0.00183
Haiku 4.5 $0.00002 $0.00091

Measured 6d ago against content hash da2d8af78ed3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

init-deep 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 6d 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.

.clinerules/skills/init-deep/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Init-Deep — Hierarchical Context Generation

Use this skill to generate AGENTS.md files at each directory level in the project. Agents automatically read the relevant AGENTS.md when working in that directory.


What It Generates

project/
├── AGENTS.md              # Project-wide context (stack, conventions, commands)
├── src/
│   ├── AGENTS.md          # src-specific context (architecture, patterns)
│   ├── routes/
│   │   ├── AGENTS.md      # Routes context (endpoint patterns, auth)
│   │   └── users/
│   │       └── AGENTS.md  # Users context (user-specific patterns)
│   ├── services/
│   │   └── AGENTS.md      # Services context (service layer patterns)
│   └── models/
│       └── AGENTS.md      # Models context (ORM patterns, relationships)
├── tests/
│   └── AGENTS.md          # Tests context (test patterns, fixtures)
└── migrations/
    └── AGENTS.md          # Migrations context (Alembic patterns)

Usage

/init-deep [--max-depth=3]
Option Default Description
--max-depth 3 Maximum directory depth to generate AGENTS.md

AGENTS.md Template

Each AGENTS.md contains:

# <Directory> Context

## Purpose
What this directory contains and its role in the project.

## Patterns
Common patterns used in this directory.

## Conventions
Naming, structure, and style conventions.

## Key Files
Important files in this directory and what they do.

## Related Directories
Parent and child directories and their relationships.

Example: src/routes/AGENTS.md

# Routes Context

## Purpose
FastAPI route definitions. Each route file maps to an endpoint group.

## Patterns
- Router pattern: `router = APIRouter(prefix="/users", tags=["users"])`
- Dependency injection: `db: AsyncSession = Depends(get_db)`
- Response models: `response_model=UserResponse`
- Error handling: `raise HTTPException(status_code=404, detail="...")`

## Conventions
- One router per resource (users.py, products.py, reviews.py)
- Endpoints: list (GET /), create (POST /), read (GET /{id}), update (PATCH /{id}), delete (DELETE /{id})
- Use snake_case for route paths, camelCase for JSON
- All endpoints must be async

## Key Files
- `users.py` — User CRUD endpoints
- `auth.py` — Authentication endpoints (login, register, refresh)
- `reviews.py` — Product review endpoints

## Related Directories
- Parent: `src/` — Application source
- Sibling: `src/services/` — Business logic (routes call services)
- Sibling: `src/models/` — Database models (routes use models via services)

Read the full file on GitHub · 145 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. 6d ago First seen · 145 lines · 21 tokens per session scan A da2d8af78ed3

Subscribe to this mod's changes

init-deep is a skill published in the GitHub repository ils15/pantheon-legacy (10 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 913 once invoked, about $0.0001 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens