init-deep
Generate hierarchical AGENTS.md files throughout the project for token-efficient agent context.
Skill by Kyou12138
Chalk Labs
Need help deploying init-deep?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kyou12138-init-deep
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/init-deep
What's inside
- Skill name
init-deep- Description
- Generate hierarchical AGENTS.md files throughout the project for token-efficient agent context. Use /init-deep.
- License
- MIT
- Instructions
- 34 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /init-deep Create directory-scoped `AGENTS.md` files so agents pick up local conventions. ## Usage ``` /init-deep /init-deep --max-depth=3 /init-deep --create-new --max-depth=2 ``` | Flag | Meaning | |------|---------| | `--max-depth=N` | How deep to walk from workspace root (default 3, max 8) | | `--create-new` | Prefer creating stubs (default behavior for empty/missing) | ## Behavior 1. Walks the tree (skips `node_modules`, `.git`, `dist`, …). 2. Writes `AGENTS.md` at root and code-bearing directories. 3. Does **not** overwrite large hand-written AGENTS.md (keeps user content). ## After generation 1. Edit stubs with real build/test commands and conventions. 2. Agents auto-receive nearby AGENTS.md via directory inject after Read. ## Related - Root `AGENTS.md` / `rules/*` still inject on every UserPrompt. - omo equivalent: `/init-deep` hierarchical knowledge base.
From Kyou12138/oh-my-grok, MIT.
More from Kyou12138/oh-my-grok
- 0.511score
ulw-loop
Kyou12138
Ultrawork loop v2 — phase machine explore→implement→verify, hard DONE gate, progress logs.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
using-superpowers
Kyou12138
Bootstrap Superpowers methodology inside oh-my-grok.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
hashline-edit
Kyou12138
Safe edits with oh-my-grok Hashline — Read first, LINE#ID anchors, no stale StrReplace.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
prometheus-plan
Kyou12138
Prometheus interview planning.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
ralph-loop
Kyou12138
Start a work-until-done Ralph loop.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
sisyphus-orchestration
Kyou12138
How Sisyphus should delegate to explore/oracle/librarian/hephaestus/atlas/prometheus.
SkillCFreshness: C★ 3Claude Code +9 - 0.503score
agent-skill-gate
Kyou12138
Meta-skill — how oh-my-grok Skill Gate works.
SkillCFreshness: C★ 3Claude Code +9 - 0.503score
handoff
Kyou12138
Write a session handoff summary for the next chat.
SkillCFreshness: C★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 11, 2026 (3 months ago)
- Last release
- Jul 16, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Kyou12138/oh-my-grok
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Kyou12138
- 0.511score
ulw-loop
Kyou12138
Ultrawork loop v2 — phase machine explore→implement→verify, hard DONE gate, progress logs.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
using-superpowers
Kyou12138
Bootstrap Superpowers methodology inside oh-my-grok.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
hashline-edit
Kyou12138
Safe edits with oh-my-grok Hashline — Read first, LINE#ID anchors, no stale StrReplace.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
prometheus-plan
Kyou12138
Prometheus interview planning.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
ralph-loop
Kyou12138
Start a work-until-done Ralph loop.
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
sisyphus-orchestration
Kyou12138
How Sisyphus should delegate to explore/oracle/librarian/hephaestus/atlas/prometheus.
SkillCFreshness: C★ 3Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get init-deep running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
init-deep skill. Agent Mart. https://agentmart.dev/skills/kyou12138-init-deep (last updated 2026-10-24)