Restructure /init-deep command prompt with dynamic phases and concurrent execution
- Reduce phases: 5 → 4 (discovery, scoring, generate, review) - Implement concurrent execution: fire background explore agents + LSP simultaneously - Add dynamic agent spawning based on project scale (files, lines, depth, large files, monorepo, languages) - Convert to telegraphic style: ~50% shorter (~427 → ~301 lines) - Clarify --create-new behavior: read existing → delete → regenerate Addresses issue #368 requirements for dynamic agent spawning and concurrent explore+LSP execution. 🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
This commit is contained in:
YeonGyu-Kim
@@ -1,228 +1,191 @@
|
|||||||
export const INIT_DEEP_TEMPLATE = `# Initialize Deep Knowledge Base
|
export const INIT_DEEP_TEMPLATE = `# /init-deep
|
||||||
|
|
||||||
Generate comprehensive AGENTS.md files across project hierarchy. Combines root-level project knowledge (gen-knowledge) with complexity-based subdirectory documentation (gen-knowledge-deep).
|
Generate hierarchical AGENTS.md files. Root + complexity-scored subdirectories.
|
||||||
|
|
||||||
## Usage
|
## Usage
|
||||||
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
/init-deep # Analyze and generate hierarchical AGENTS.md
|
/init-deep # Update mode: modify existing + create new where warranted
|
||||||
/init-deep --create-new # Force create from scratch (ignore existing)
|
/init-deep --create-new # Read existing → remove all → regenerate from scratch
|
||||||
/init-deep --max-depth=2 # Limit to N directory levels (default: 3)
|
/init-deep --max-depth=2 # Limit directory depth (default: 3)
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Core Principles
|
## Workflow (High-Level)
|
||||||
|
|
||||||
- **Telegraphic Style**: Sacrifice grammar for concision ("Project uses React" → "React 18")
|
1. **Discovery + Analysis** (concurrent)
|
||||||
- **Predict-then-Compare**: Predict standard → find actual → document ONLY deviations
|
- Fire background explore agents immediately
|
||||||
- **Hierarchy Aware**: Parent covers general, children cover specific
|
- Main session: bash structure + LSP codemap + read existing AGENTS.md
|
||||||
- **No Redundancy**: Child AGENTS.md NEVER repeats parent content
|
2. **Score & Decide** - Determine AGENTS.md locations from merged findings
|
||||||
- **LSP-First**: Use LSP tools for accurate code intelligence when available (semantic > text search)
|
3. **Generate** - Root first, then subdirs in parallel
|
||||||
|
4. **Review** - Deduplicate, trim, validate
|
||||||
---
|
|
||||||
|
|
||||||
## Process
|
|
||||||
|
|
||||||
<critical>
|
<critical>
|
||||||
**MANDATORY: TodoWrite for ALL phases. Mark in_progress → completed in real-time.**
|
**TodoWrite ALL phases. Mark in_progress → completed in real-time.**
|
||||||
</critical>
|
|
||||||
|
|
||||||
### Phase 0: Initialize
|
|
||||||
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
TodoWrite([
|
TodoWrite([
|
||||||
{ id: "p1-analysis", content: "Parallel project structure & complexity analysis", status: "pending", priority: "high" },
|
{ id: "discovery", content: "Fire explore agents + LSP codemap + read existing", status: "pending", priority: "high" },
|
||||||
{ id: "p2-scoring", content: "Score directories, determine AGENTS.md locations", status: "pending", priority: "high" },
|
{ id: "scoring", content: "Score directories, determine locations", status: "pending", priority: "high" },
|
||||||
{ id: "p3-root", content: "Generate root AGENTS.md with Predict-then-Compare", status: "pending", priority: "high" },
|
{ id: "generate", content: "Generate AGENTS.md files (root + subdirs)", status: "pending", priority: "high" },
|
||||||
{ id: "p4-subdirs", content: "Generate subdirectory AGENTS.md files in parallel", status: "pending", priority: "high" },
|
{ id: "review", content: "Deduplicate, validate, trim", status: "pending", priority: "medium" }
|
||||||
{ id: "p5-review", content: "Review, deduplicate, validate all files", status: "pending", priority: "medium" }
|
|
||||||
])
|
])
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Phase 1: Parallel Project Analysis
|
|
||||||
|
|
||||||
**Mark "p1-analysis" as in_progress.**
|
|
||||||
|
|
||||||
<critical>
|
|
||||||
**EXECUTION PATTERN**: Fire background agents FIRST (non-blocking), then main session builds codemap understanding using LSP tools in parallel. This maximizes throughput—agents discover while you analyze.
|
|
||||||
</critical>
|
</critical>
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
### Step 1: Fire Background Explore Agents (IMMEDIATELY)
|
## Phase 1: Discovery + Analysis (Concurrent)
|
||||||
|
|
||||||
Fire ALL background tasks at once. They run asynchronously—don't wait for results yet.
|
**Mark "discovery" as in_progress.**
|
||||||
|
|
||||||
|
### Fire Background Explore Agents IMMEDIATELY
|
||||||
|
|
||||||
|
Don't wait—these run async while main session works.
|
||||||
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
// Fire immediately - these run in parallel, non-blocking
|
// Fire all at once, collect results later
|
||||||
background_task(agent="explore", prompt="Project structure: PREDICT standard {lang} patterns → FIND package.json/pyproject.toml/go.mod → REPORT deviations only")
|
background_task(agent="explore", prompt="Project structure: PREDICT standard patterns for detected language → REPORT deviations only")
|
||||||
|
background_task(agent="explore", prompt="Entry points: FIND main files → REPORT non-standard organization")
|
||||||
background_task(agent="explore", prompt="Entry points: PREDICT typical (main.py, index.ts) → FIND actual → REPORT non-standard organization")
|
background_task(agent="explore", prompt="Conventions: FIND config files (.eslintrc, pyproject.toml, .editorconfig) → REPORT project-specific rules")
|
||||||
|
background_task(agent="explore", prompt="Anti-patterns: FIND 'DO NOT', 'NEVER', 'ALWAYS', 'DEPRECATED' comments → LIST forbidden patterns")
|
||||||
background_task(agent="explore", prompt="Conventions: FIND .cursor/rules, .cursorrules, eslintrc, pyproject.toml → REPORT project-specific rules DIFFERENT from defaults")
|
background_task(agent="explore", prompt="Build/CI: FIND .github/workflows, Makefile → REPORT non-standard patterns")
|
||||||
|
background_task(agent="explore", prompt="Test patterns: FIND test configs, test structure → REPORT unique conventions")
|
||||||
background_task(agent="explore", prompt="Anti-patterns: FIND comments with 'DO NOT', 'NEVER', 'ALWAYS', 'LEGACY', 'DEPRECATED' → REPORT forbidden patterns")
|
|
||||||
|
|
||||||
background_task(agent="explore", prompt="Build/CI: FIND .github/workflows, Makefile, justfile → REPORT non-standard build/deploy patterns")
|
|
||||||
|
|
||||||
background_task(agent="explore", prompt="Test patterns: FIND pytest.ini, jest.config, test structure → REPORT unique testing conventions")
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
---
|
<dynamic-agents>
|
||||||
|
**DYNAMIC AGENT SPAWNING**: After bash analysis, spawn ADDITIONAL explore agents based on project scale:
|
||||||
|
|
||||||
### Step 2: Main Session Codemap Understanding (while background runs)
|
| Factor | Threshold | Additional Agents |
|
||||||
|
|--------|-----------|-------------------|
|
||||||
|
| **Total files** | >100 | +1 per 100 files |
|
||||||
|
| **Total lines** | >10k | +1 per 10k lines |
|
||||||
|
| **Directory depth** | ≥4 | +2 for deep exploration |
|
||||||
|
| **Large files (>500 lines)** | >10 files | +1 for complexity hotspots |
|
||||||
|
| **Monorepo** | detected | +1 per package/workspace |
|
||||||
|
| **Multiple languages** | >1 | +1 per language |
|
||||||
|
|
||||||
While background agents discover patterns, main session builds codemap understanding using direct tools.
|
|
||||||
|
|
||||||
<parallel-tools>
|
|
||||||
|
|
||||||
#### Structural Analysis (bash)
|
|
||||||
\`\`\`bash
|
\`\`\`bash
|
||||||
# Task A: Directory depth analysis
|
# Measure project scale first
|
||||||
find . -type d -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/__pycache__/*' -not -path '*/dist/*' -not -path '*/build/*' | awk -F/ '{print NF-1}' | sort -n | uniq -c
|
total_files=$(find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | wc -l)
|
||||||
|
total_lines=$(find . -type f \\( -name "*.ts" -o -name "*.py" -o -name "*.go" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | tail -1 | awk '{print $1}')
|
||||||
|
large_files=$(find . -type f \\( -name "*.ts" -o -name "*.py" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | awk '$1 > 500 {count++} END {print count+0}')
|
||||||
|
max_depth=$(find . -type d -not -path '*/node_modules/*' -not -path '*/.git/*' | awk -F/ '{print NF}' | sort -rn | head -1)
|
||||||
|
\`\`\`
|
||||||
|
|
||||||
# Task B: File count per directory
|
Example spawning:
|
||||||
find . -type f -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/__pycache__/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -30
|
\`\`\`
|
||||||
|
// 500 files, 50k lines, depth 6, 15 large files → spawn 5+5+2+1 = 13 additional agents
|
||||||
|
background_task(agent="explore", prompt="Large file analysis: FIND files >500 lines, REPORT complexity hotspots")
|
||||||
|
background_task(agent="explore", prompt="Deep modules at depth 4+: FIND hidden patterns, internal conventions")
|
||||||
|
background_task(agent="explore", prompt="Cross-cutting concerns: FIND shared utilities across directories")
|
||||||
|
// ... more based on calculation
|
||||||
|
\`\`\`
|
||||||
|
</dynamic-agents>
|
||||||
|
|
||||||
# Task C: Code concentration
|
### Main Session: Concurrent Analysis
|
||||||
find . -type f \\( -name "*.py" -o -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.jsx" -o -name "*.go" -o -name "*.rs" -o -name "*.java" \\) -not -path '*/node_modules/*' -not -path '*/venv/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -20
|
|
||||||
|
|
||||||
# Task D: Existing knowledge files
|
**While background agents run**, main session does:
|
||||||
|
|
||||||
|
#### 1. Bash Structural Analysis
|
||||||
|
\`\`\`bash
|
||||||
|
# Directory depth + file counts
|
||||||
|
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
|
||||||
|
|
||||||
|
# Files per directory (top 30)
|
||||||
|
find . -type f -not -path '*/\\.*' -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -30
|
||||||
|
|
||||||
|
# Code concentration by extension
|
||||||
|
find . -type f \\( -name "*.py" -o -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.go" -o -name "*.rs" \\) -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -20
|
||||||
|
|
||||||
|
# Existing AGENTS.md / CLAUDE.md
|
||||||
find . -type f \\( -name "AGENTS.md" -o -name "CLAUDE.md" \\) -not -path '*/node_modules/*' 2>/dev/null
|
find . -type f \\( -name "AGENTS.md" -o -name "CLAUDE.md" \\) -not -path '*/node_modules/*' 2>/dev/null
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
#### LSP Codemap Analysis (main session - semantic understanding)
|
#### 2. Read Existing AGENTS.md
|
||||||
|
|
||||||
LSP provides semantic understanding beyond text search. Build the codemap while background agents run.
|
|
||||||
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
# Check LSP availability first
|
For each existing file found:
|
||||||
lsp_servers() # Verify language server is available
|
Read(filePath=file)
|
||||||
|
Extract: key insights, conventions, anti-patterns
|
||||||
# Analyze entry point files (run in parallel)
|
Store in EXISTING_AGENTS map
|
||||||
lsp_document_symbols(filePath="src/index.ts") # Main entry
|
|
||||||
lsp_document_symbols(filePath="src/main.py") # Python entry
|
|
||||||
lsp_document_symbols(filePath="cmd/main.go") # Go entry
|
|
||||||
|
|
||||||
# Discover key symbols across workspace (run in parallel)
|
|
||||||
lsp_workspace_symbols(filePath=".", query="class") # All classes
|
|
||||||
lsp_workspace_symbols(filePath=".", query="interface") # All interfaces
|
|
||||||
lsp_workspace_symbols(filePath=".", query="function") # Top-level functions
|
|
||||||
lsp_workspace_symbols(filePath=".", query="type") # Type definitions
|
|
||||||
|
|
||||||
# Analyze symbol centrality (for top 5-10 key symbols)
|
|
||||||
# High reference count = central/important concept
|
|
||||||
lsp_find_references(filePath="src/index.ts", line=X, character=Y) # Main export
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
</parallel-tools>
|
If \`--create-new\`: Read all existing first (preserve context) → then delete all → regenerate.
|
||||||
|
|
||||||
#### Codemap Output Format
|
|
||||||
|
|
||||||
|
#### 3. LSP Codemap (if available)
|
||||||
\`\`\`
|
\`\`\`
|
||||||
CODE_INTELLIGENCE = {
|
lsp_servers() # Check availability
|
||||||
entry_points: [
|
|
||||||
{ file: "src/index.ts", exports: ["Plugin", "createHook"], symbol_count: 12 }
|
# Entry points (parallel)
|
||||||
],
|
lsp_document_symbols(filePath="src/index.ts")
|
||||||
key_symbols: [
|
lsp_document_symbols(filePath="main.py")
|
||||||
{ name: "Plugin", type: "class", file: "src/index.ts", refs: 45, role: "Central orchestrator" },
|
|
||||||
{ name: "createHook", type: "function", file: "src/utils.ts", refs: 23, role: "Hook factory" }
|
# Key symbols (parallel)
|
||||||
],
|
lsp_workspace_symbols(filePath=".", query="class")
|
||||||
module_boundaries: [
|
lsp_workspace_symbols(filePath=".", query="interface")
|
||||||
{ dir: "src/hooks", exports: 21, imports_from: ["shared/"] },
|
lsp_workspace_symbols(filePath=".", query="function")
|
||||||
{ dir: "src/tools", exports: 15, imports_from: ["shared/", "hooks/"] }
|
|
||||||
]
|
# Centrality for top exports
|
||||||
}
|
lsp_find_references(filePath="...", line=X, character=Y)
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
<critical>
|
**LSP Fallback**: If unavailable, rely on explore agents + AST-grep.
|
||||||
**LSP Fallback**: If LSP unavailable (no server installed), skip LSP section and rely on explore agents + AST-grep patterns.
|
|
||||||
</critical>
|
### Collect Background Results
|
||||||
|
|
||||||
|
\`\`\`
|
||||||
|
// After main session analysis done, collect all task results
|
||||||
|
for each task_id: background_output(task_id="...")
|
||||||
|
\`\`\`
|
||||||
|
|
||||||
|
**Merge: bash + LSP + existing + explore findings. Mark "discovery" as completed.**
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
### Step 3: Collect Background Results
|
## Phase 2: Scoring & Location Decision
|
||||||
|
|
||||||
After main session analysis complete, collect background agent results:
|
**Mark "scoring" as in_progress.**
|
||||||
|
|
||||||
\`\`\`
|
|
||||||
// Collect all background_task results
|
|
||||||
// background_output(task_id="...") for each fired task
|
|
||||||
\`\`\`
|
|
||||||
|
|
||||||
**Merge bash + LSP + background agent findings. Mark "p1-analysis" as completed.**
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Phase 2: Complexity Scoring & Location Decision
|
|
||||||
|
|
||||||
**Mark "p2-scoring" as in_progress.**
|
|
||||||
|
|
||||||
### Scoring Matrix
|
### Scoring Matrix
|
||||||
|
|
||||||
| Factor | Weight | Threshold | Source |
|
| Factor | Weight | High Threshold | Source |
|
||||||
|--------|--------|-----------|--------|
|
|--------|--------|----------------|--------|
|
||||||
| File count | 3x | >20 files = high | bash |
|
| File count | 3x | >20 | bash |
|
||||||
| Subdirectory count | 2x | >5 subdirs = high | bash |
|
| Subdir count | 2x | >5 | bash |
|
||||||
| Code file ratio | 2x | >70% code = high | bash |
|
| Code ratio | 2x | >70% | bash |
|
||||||
| Unique patterns | 1x | Has own config | explore |
|
| Unique patterns | 1x | Has own config | explore |
|
||||||
| Module boundary | 2x | Has __init__.py/index.ts | bash |
|
| Module boundary | 2x | Has index.ts/__init__.py | bash |
|
||||||
| **Symbol density** | 2x | >30 symbols = high | LSP |
|
| Symbol density | 2x | >30 symbols | LSP |
|
||||||
| **Export count** | 2x | >10 exports = high | LSP |
|
| Export count | 2x | >10 exports | LSP |
|
||||||
| **Reference centrality** | 3x | Symbols with >20 refs | LSP |
|
| Reference centrality | 3x | >20 refs | LSP |
|
||||||
|
|
||||||
<lsp-scoring>
|
|
||||||
**LSP-Enhanced Scoring** (if available):
|
|
||||||
|
|
||||||
\`\`\`
|
|
||||||
For each directory in candidates:
|
|
||||||
symbols = lsp_document_symbols(dir/index.ts or dir/__init__.py)
|
|
||||||
|
|
||||||
symbol_score = len(symbols) > 30 ? 6 : len(symbols) > 15 ? 3 : 0
|
|
||||||
export_score = count(exported symbols) > 10 ? 4 : 0
|
|
||||||
|
|
||||||
# Check if this module is central (many things depend on it)
|
|
||||||
for each exported symbol:
|
|
||||||
refs = lsp_find_references(symbol)
|
|
||||||
if refs > 20: centrality_score += 3
|
|
||||||
|
|
||||||
total_score += symbol_score + export_score + centrality_score
|
|
||||||
\`\`\`
|
|
||||||
</lsp-scoring>
|
|
||||||
|
|
||||||
### Decision Rules
|
### Decision Rules
|
||||||
|
|
||||||
| Score | Action |
|
| Score | Action |
|
||||||
|-------|--------|
|
|-------|--------|
|
||||||
| **Root (.)** | ALWAYS create AGENTS.md |
|
| **Root (.)** | ALWAYS create |
|
||||||
| **High (>15)** | Create dedicated AGENTS.md |
|
| **>15** | Create AGENTS.md |
|
||||||
| **Medium (8-15)** | Create if distinct domain |
|
| **8-15** | Create if distinct domain |
|
||||||
| **Low (<8)** | Skip, parent sufficient |
|
| **<8** | Skip (parent covers) |
|
||||||
|
|
||||||
### Output Format
|
|
||||||
|
|
||||||
|
### Output
|
||||||
\`\`\`
|
\`\`\`
|
||||||
AGENTS_LOCATIONS = [
|
AGENTS_LOCATIONS = [
|
||||||
{ path: ".", type: "root" },
|
{ path: ".", type: "root" },
|
||||||
{ path: "src/api", score: 18, reason: "high complexity, 45 files" },
|
{ path: "src/hooks", score: 18, reason: "high complexity" },
|
||||||
{ path: "src/hooks", score: 12, reason: "distinct domain, unique patterns" },
|
{ path: "src/api", score: 12, reason: "distinct domain" }
|
||||||
]
|
]
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
**Mark "p2-scoring" as completed.**
|
**Mark "scoring" as completed.**
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Phase 3: Generate Root AGENTS.md
|
## Phase 3: Generate AGENTS.md
|
||||||
|
|
||||||
**Mark "p3-root" as in_progress.**
|
**Mark "generate" as in_progress.**
|
||||||
|
|
||||||
Root AGENTS.md gets **full treatment** with Predict-then-Compare synthesis.
|
### Root AGENTS.md (Full Treatment)
|
||||||
|
|
||||||
### Required Sections
|
|
||||||
|
|
||||||
\`\`\`markdown
|
\`\`\`markdown
|
||||||
# PROJECT KNOWLEDGE BASE
|
# PROJECT KNOWLEDGE BASE
|
||||||
@@ -232,153 +195,75 @@ Root AGENTS.md gets **full treatment** with Predict-then-Compare synthesis.
|
|||||||
**Branch:** {BRANCH}
|
**Branch:** {BRANCH}
|
||||||
|
|
||||||
## OVERVIEW
|
## OVERVIEW
|
||||||
|
{1-2 sentences: what + core stack}
|
||||||
{1-2 sentences: what project does, core tech stack}
|
|
||||||
|
|
||||||
## STRUCTURE
|
## STRUCTURE
|
||||||
|
|
||||||
\\\`\\\`\\\`
|
\\\`\\\`\\\`
|
||||||
{project-root}/
|
{root}/
|
||||||
├── {dir}/ # {non-obvious purpose only}
|
├── {dir}/ # {non-obvious purpose only}
|
||||||
└── {entry} # entry point
|
└── {entry}
|
||||||
\\\`\\\`\\\`
|
\\\`\\\`\\\`
|
||||||
|
|
||||||
## WHERE TO LOOK
|
## WHERE TO LOOK
|
||||||
|
|
||||||
| Task | Location | Notes |
|
| Task | Location | Notes |
|
||||||
|------|----------|-------|
|
|------|----------|-------|
|
||||||
| Add feature X | \\\`src/x/\\\` | {pattern hint} |
|
|
||||||
|
|
||||||
## CODE MAP
|
## CODE MAP
|
||||||
|
{From LSP - skip if unavailable or project <10 files}
|
||||||
{Generated from LSP analysis - shows key symbols and their relationships}
|
|
||||||
|
|
||||||
| Symbol | Type | Location | Refs | Role |
|
| Symbol | Type | Location | Refs | Role |
|
||||||
|--------|------|----------|------|------|
|
|--------|------|----------|------|------|
|
||||||
| {MainClass} | Class | \\\`src/index.ts\\\` | {N} | {Central orchestrator} |
|
|
||||||
| {createX} | Function | \\\`src/utils.ts\\\` | {N} | {Factory pattern} |
|
|
||||||
| {Config} | Interface | \\\`src/types.ts\\\` | {N} | {Configuration contract} |
|
|
||||||
|
|
||||||
### Module Dependencies
|
|
||||||
|
|
||||||
\\\`\\\`\\\`
|
|
||||||
{entry} ──imports──> {core/}
|
|
||||||
│ │
|
|
||||||
└──imports──> {utils/} <──imports── {features/}
|
|
||||||
\\\`\\\`\\\`
|
|
||||||
|
|
||||||
<code-map-note>
|
|
||||||
**Skip CODE MAP if**: LSP unavailable OR project too small (<10 files) OR no clear module boundaries.
|
|
||||||
</code-map-note>
|
|
||||||
|
|
||||||
## CONVENTIONS
|
## CONVENTIONS
|
||||||
|
{ONLY deviations from standard}
|
||||||
{ONLY deviations from standard - skip generic advice}
|
|
||||||
|
|
||||||
- **{rule}**: {specific detail}
|
|
||||||
|
|
||||||
## ANTI-PATTERNS (THIS PROJECT)
|
## ANTI-PATTERNS (THIS PROJECT)
|
||||||
|
{Explicitly forbidden here}
|
||||||
{Things explicitly forbidden HERE}
|
|
||||||
|
|
||||||
- **{pattern}**: {why} → {alternative}
|
|
||||||
|
|
||||||
## UNIQUE STYLES
|
## UNIQUE STYLES
|
||||||
|
{Project-specific}
|
||||||
{Project-specific coding styles}
|
|
||||||
|
|
||||||
- **{style}**: {how different}
|
|
||||||
|
|
||||||
## COMMANDS
|
## COMMANDS
|
||||||
|
|
||||||
\\\`\\\`\\\`bash
|
\\\`\\\`\\\`bash
|
||||||
{dev-command}
|
{dev/test/build}
|
||||||
{test-command}
|
|
||||||
{build-command}
|
|
||||||
\\\`\\\`\\\`
|
\\\`\\\`\\\`
|
||||||
|
|
||||||
## NOTES
|
## NOTES
|
||||||
|
{Gotchas}
|
||||||
{Gotchas, non-obvious info}
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
### Quality Gates
|
**Quality gates**: 50-150 lines, no generic advice, no obvious info.
|
||||||
|
|
||||||
- [ ] Size: 50-150 lines
|
### Subdirectory AGENTS.md (Parallel)
|
||||||
- [ ] No generic advice ("write clean code")
|
|
||||||
- [ ] No obvious info ("tests/ has tests")
|
|
||||||
- [ ] Every item is project-specific
|
|
||||||
|
|
||||||
**Mark "p3-root" as completed.**
|
Launch document-writer agents for each location:
|
||||||
|
|
||||||
|
\`\`\`
|
||||||
|
for loc in AGENTS_LOCATIONS (except root):
|
||||||
|
background_task(agent="document-writer", prompt=\\\`
|
||||||
|
Generate AGENTS.md for: \${loc.path}
|
||||||
|
- Reason: \${loc.reason}
|
||||||
|
- 30-80 lines max
|
||||||
|
- NEVER repeat parent content
|
||||||
|
- Sections: OVERVIEW (1 line), STRUCTURE (if >5 subdirs), WHERE TO LOOK, CONVENTIONS (if different), ANTI-PATTERNS
|
||||||
|
\\\`)
|
||||||
|
\`\`\`
|
||||||
|
|
||||||
|
**Wait for all. Mark "generate" as completed.**
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Phase 4: Generate Subdirectory AGENTS.md
|
## Phase 4: Review & Deduplicate
|
||||||
|
|
||||||
**Mark "p4-subdirs" as in_progress.**
|
**Mark "review" as in_progress.**
|
||||||
|
|
||||||
For each location in AGENTS_LOCATIONS (except root), launch **parallel document-writer agents**:
|
For each generated file:
|
||||||
|
- Remove generic advice
|
||||||
|
- Remove parent duplicates
|
||||||
|
- Trim to size limits
|
||||||
|
- Verify telegraphic style
|
||||||
|
|
||||||
\`\`\`typescript
|
**Mark "review" as completed.**
|
||||||
for (const loc of AGENTS_LOCATIONS.filter(l => l.path !== ".")) {
|
|
||||||
background_task({
|
|
||||||
agent: "document-writer",
|
|
||||||
prompt: \\\`
|
|
||||||
Generate AGENTS.md for: \${loc.path}
|
|
||||||
|
|
||||||
CONTEXT:
|
|
||||||
- Complexity reason: \${loc.reason}
|
|
||||||
- Parent AGENTS.md: ./AGENTS.md (already covers project overview)
|
|
||||||
|
|
||||||
CRITICAL RULES:
|
|
||||||
1. Focus ONLY on this directory's specific context
|
|
||||||
2. NEVER repeat parent AGENTS.md content
|
|
||||||
3. Shorter is better - 30-80 lines max
|
|
||||||
4. Telegraphic style - sacrifice grammar
|
|
||||||
|
|
||||||
REQUIRED SECTIONS:
|
|
||||||
- OVERVIEW (1 line: what this directory does)
|
|
||||||
- STRUCTURE (only if >5 subdirs)
|
|
||||||
- WHERE TO LOOK (directory-specific tasks)
|
|
||||||
- CONVENTIONS (only if DIFFERENT from root)
|
|
||||||
- ANTI-PATTERNS (directory-specific only)
|
|
||||||
|
|
||||||
OUTPUT: Write to \${loc.path}/AGENTS.md
|
|
||||||
\\\`
|
|
||||||
})
|
|
||||||
}
|
|
||||||
\`\`\`
|
|
||||||
|
|
||||||
**Wait for all agents. Mark "p4-subdirs" as completed.**
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Phase 5: Review & Deduplicate
|
|
||||||
|
|
||||||
**Mark "p5-review" as in_progress.**
|
|
||||||
|
|
||||||
### Validation Checklist
|
|
||||||
|
|
||||||
For EACH generated AGENTS.md:
|
|
||||||
|
|
||||||
| Check | Action if Fail |
|
|
||||||
|-------|----------------|
|
|
||||||
| Contains generic advice | REMOVE the line |
|
|
||||||
| Repeats parent content | REMOVE the line |
|
|
||||||
| Missing required section | ADD it |
|
|
||||||
| Over 150 lines (root) / 80 lines (subdir) | TRIM |
|
|
||||||
| Verbose explanations | REWRITE telegraphic |
|
|
||||||
|
|
||||||
### Cross-Reference Validation
|
|
||||||
|
|
||||||
\`\`\`
|
|
||||||
For each child AGENTS.md:
|
|
||||||
For each line in child:
|
|
||||||
If similar line exists in parent:
|
|
||||||
REMOVE from child (parent already covers)
|
|
||||||
\`\`\`
|
|
||||||
|
|
||||||
**Mark "p5-review" as completed.**
|
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
@@ -387,31 +272,29 @@ For each child AGENTS.md:
|
|||||||
\`\`\`
|
\`\`\`
|
||||||
=== init-deep Complete ===
|
=== init-deep Complete ===
|
||||||
|
|
||||||
Files Generated:
|
Mode: {update | create-new}
|
||||||
|
|
||||||
|
Files:
|
||||||
✓ ./AGENTS.md (root, {N} lines)
|
✓ ./AGENTS.md (root, {N} lines)
|
||||||
✓ ./src/hooks/AGENTS.md ({N} lines)
|
✓ ./src/hooks/AGENTS.md ({N} lines)
|
||||||
✓ ./src/tools/AGENTS.md ({N} lines)
|
|
||||||
|
|
||||||
Directories Analyzed: {N}
|
Dirs Analyzed: {N}
|
||||||
AGENTS.md Created: {N}
|
AGENTS.md Created: {N}
|
||||||
Total Lines: {N}
|
AGENTS.md Updated: {N}
|
||||||
|
|
||||||
Hierarchy:
|
Hierarchy:
|
||||||
./AGENTS.md
|
./AGENTS.md
|
||||||
├── src/hooks/AGENTS.md
|
└── src/hooks/AGENTS.md
|
||||||
└── src/tools/AGENTS.md
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Anti-Patterns for THIS Command
|
## Anti-Patterns
|
||||||
|
|
||||||
- **Over-documenting**: Not every directory needs AGENTS.md
|
- **Static agent count**: MUST vary agents based on project size/depth
|
||||||
- **Redundancy**: Child must NOT repeat parent
|
- **Sequential execution**: MUST parallel (explore + LSP concurrent)
|
||||||
|
- **Ignoring existing**: ALWAYS read existing first, even with --create-new
|
||||||
|
- **Over-documenting**: Not every dir needs AGENTS.md
|
||||||
|
- **Redundancy**: Child never repeats parent
|
||||||
- **Generic content**: Remove anything that applies to ALL projects
|
- **Generic content**: Remove anything that applies to ALL projects
|
||||||
- **Sequential execution**: MUST use parallel agents
|
- **Verbose style**: Telegraphic or die`
|
||||||
- **Deep nesting**: Rarely need AGENTS.md at depth 4+
|
|
||||||
- **Verbose style**: "This directory contains..." → just list it
|
|
||||||
- **Ignoring LSP**: If LSP available, USE IT - semantic analysis > text grep
|
|
||||||
- **LSP without fallback**: Always have explore agent backup if LSP unavailable
|
|
||||||
- **Over-referencing**: Don't trace refs for EVERY symbol - focus on exports only`
|
|
||||||
|
|||||||
Reference in New Issue
Block a user