init-deep
Use to generate or refresh hierarchical AGENTS.md files for a new, unfamiliar or restructured codebase ("init deep", "generate AGENTS.md").
Skill by UtsavBalar1231
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/utsavbalar1231-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
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 and code. Checked Oct 26, 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
- Use to generate or refresh hierarchical AGENTS.md files for a new, unfamiliar or restructured codebase ("init deep", "generate AGENTS.md").
- License
- MIT
- Instructions
- 108 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /init-deep
Generate hierarchical AGENTS.md files. Root + complexity-scored subdirectories.
## Usage
```
/init-deep # Update mode: modify existing + create new where warranted
/init-deep --create-new # Read existing → remove all → regenerate from scratch
```
## Workflow
1. **Discovery + Analysis** (concurrent): explorer agents, bash structure, codemap, existing AGENTS.md
2. **Score & Decide**: AGENTS.md locations from merged findings
3. **Generate**: root first, subdirs in parallel
4. **Review**: deduplicate, trim, validate
## Phase 1: discovery + analysis (concurrent)
### Background explorer agents
Each explorer agent re-reads the repository from scratch and hands back a report you then read, so delegate only the tracks the Bash pass below cannot answer in a few reads: none for a small repository, and at most five in total for a large one. Launch the ones you choose in a single message so they run concurrently, and brief each with its directory scope and what to report. Candidate tracks:
- Entry points and non-standard organization
- Config files (.eslintrc, pyproject.toml, .editorconfig) and the project-specific rules they encode
- Comments that mark forbidden or deprecated patterns (`DO NOT`, `NEVER`, `DEPRECATED`), with the reason each gives
- Build and CI (.github/workflows, Makefile) where it departs from the defaults
- Test configuration and layout
### Background agent barrier
Merge the explorer findings only after every agent has reported. Until then, carry on with the main-session analysis below, which does not overlap theirs; when it is done and agents are still running, end the turn once instead of answering each notification with a holding message.
### Main session (concurrent with agents)
#### 1. Bash structural analysis
```bash
find . -type d -not -path '*/\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/dist/*' -not -path '*/build/*' | awk -F/ '{print NF-1}' | sort -n | uniq -c
find . -type f -not -path '*/\.*' -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -30
find . -type f \( -name "*.py" -o -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.go" -o -name "*.rs" \) -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -20
find . -type f \( -name "AGENTS.md" -o -name "CLAUDE.md" \) -not -path '*/node_modules/*' 2>/dev/null
```
#### 2. Read existing AGENTS.md
Extract key insights, conventions, anti-patterns. `--create-new`: read first (preserve context) → delete → regenerate.
#### 3. LSP codemap (if available)
If the `LSP` tool is active (it needs a code-intelligence plugin for the language), use it to list the symbols in entry-point files, search symbols across the workspace, and find references into heavily used modules. Otherwise rely on the explorer agents and the Bash pass.
## Phase 2: scoring & location decision
The root always gets an AGENTS.md. A subdirectory gets one when an agent working inside it would need knowledge that neither the root file nor the code in front of it supplies. Signals, strongest first:
- Its own config, build, or test commands
- A module boundary that other code imports through (`index.ts`, `__init__.py`, a public API)
- Conventions or constraints that differ from its parent
- Code much of the repository depends on (many incoming references, when the `LSP` tool is active)
- Size: many files or subdirectories make the other signals likelier without being one
Leave a directory to its parent file when the parent already covers it. Every extra file costs context in each session that loads it.
## Phase 3: generate AGENTS.md
### Root AGENTS.md
```markdown
# Project knowledge base
## Overview
{1-2 sentences: what + core stack}
## Structure
{Tree with non-obvious purposes only}
## Where to look
| Task | Location | Notes |
## Conventions
{ONLY deviations from standard}
## Anti-patterns in this project
{Explicitly forbidden here}
## Commands
{dev/test/build}
```
Quality bar: every line tells an agent something it could not infer from the code or from general knowledge of the stack. Later sessions load these files as instructions, so write each convention or constraint as a plain sentence that carries its reason, and match the length to what the directory needs, with no filler sections.
### Subdirectory AGENTS.md (parallel)
Same bar, scoped to the directory: what differs from the parent, and why.
## Phase 4: review & deduplicate
Remove generic advice and anything a parent file already says. Keep the reason attached to each rule that survives.
## Anti-patterns
- Ignoring existing files: ALWAYS read first, even with --create-new
- Over-documenting: not every dir needs AGENTS.md
- Redundancy: a child never repeats its parent
- Generic content: remove anything that applies to ALL projectsFrom UtsavBalar1231/oh-my-claudeagent, MIT.
More from UtsavBalar1231/oh-my-claudeagent
- 0.604score
consolidate-memory
UtsavBalar1231
Use when a plan finishes or agent memories have piled up.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
debugging
UtsavBalar1231
Use for runtime bugs: crashes, wrong output, intermittent or silent failures, flaky tests, code that works locally but not in prod.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
github-triage
UtsavBalar1231
Use to triage open GitHub issues and PRs in parallel, read-only, one executor per item ("triage issues", "review open PRs").
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
remove-ai-slops
UtsavBalar1231
Use to strip AI slop from changed files (double guards, dead fallbacks, narrating comments, premature abstraction) while keeping load-bearing validation and…
SkillAFreshness: A★ 3Claude Code +9 - 0.599score
build-fixer
UtsavBalar1231
Use when a build, type check or dependency install fails, or the user pastes a compiler error or says "fix build".
SkillAFreshness: A★ 3Claude Code +9 - 0.599score
refactor
UtsavBalar1231
Use when restructuring code without changing its behavior, such as extracting a module or migrating off an API.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
plan
UtsavBalar1231
Create a strategic work plan via a planner-style interview and structured plan drafting.
SkillAFreshness: A★ 3Claude Code +9 - 0.596score
reviewer
UtsavBalar1231
Rigorous plan review via the reviewer.
SkillAFreshness: A★ 3Claude Code +9 - 0.596score
omca-setup
UtsavBalar1231
Use to install, check, repair or uninstall oh-my-claudeagent's setup in ~/.claude/ (dependencies, runtime, status line), or when the user says "setup omca".
SkillAFreshness: A★ 3Claude Code +9 - 0.593score
analyzer
UtsavBalar1231
Pre-planning analysis via the analyzer.
SkillAFreshness: A★ 3Claude Code +9 - 0.589score
handoff
UtsavBalar1231
Write a self-contained context summary that a new session can continue from.
SkillAFreshness: A★ 3Claude Code +9 - 0.586score
start-work
UtsavBalar1231
Start a work session from a planner-generated plan.
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 6, 2026 (22 days ago)
- Last release
- Oct 20, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from UtsavBalar1231
- 0.604score
consolidate-memory
UtsavBalar1231
Use when a plan finishes or agent memories have piled up.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
debugging
UtsavBalar1231
Use for runtime bugs: crashes, wrong output, intermittent or silent failures, flaky tests, code that works locally but not in prod.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
github-triage
UtsavBalar1231
Use to triage open GitHub issues and PRs in parallel, read-only, one executor per item ("triage issues", "review open PRs").
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
remove-ai-slops
UtsavBalar1231
Use to strip AI slop from changed files (double guards, dead fallbacks, narrating comments, premature abstraction) while keeping load-bearing validation and…
SkillAFreshness: A★ 3Claude Code +9 - 0.599score
build-fixer
UtsavBalar1231
Use when a build, type check or dependency install fails, or the user pastes a compiler error or says "fix build".
SkillAFreshness: A★ 3Claude Code +9 - 0.599score
refactor
UtsavBalar1231
Use when restructuring code without changing its behavior, such as extracting a module or migrating off an API.
SkillAFreshness: A★ 3Claude Code +9
Cite this page
init-deep skill. Agent Mart. https://agentmart.dev/skills/utsavbalar1231-init-deep (last updated 2026-10-24)