index-knowledge

Generate hierarchical AGENTS.md files. Root + complexity-scored subdirectories.

Usage

--create-new   # Read existing → remove all → regenerate from scratch
--max-depth=2  # Limit directory depth (default: 5)

Default: Update mode (modify existing + create new where warranted)

---

Workflow (High-Level)

1. Discovery + Analysis (concurrent)
   • Launch parallel explore agents (multiple Task calls in one message)
   • Main session: bash structure + LSP codemap + read existing AGENTS.md
2. Score & Decide - Determine AGENTS.md locations from merged findings
3. Generate - Root first, then subdirs in parallel
4. Review - Deduplicate, trim, validate
5. Symlinks - CLAUDE.md → AGENTS.md per directory (see Phase 5)

TodoWrite([
  { id: "discovery", content: "Fire explore agents + LSP codemap + read existing", status: "pending", priority: "high" },
  { id: "scoring", content: "Score directories, determine locations", status: "pending", priority: "high" },
  { id: "generate", content: "Generate AGENTS.md files (root + subdirs)", status: "pending", priority: "high" },
  { id: "review", content: "Deduplicate, validate, trim", status: "pending", priority: "medium" },
  { id: "symlinks", content: "CLAUDE.md → AGENTS.md symlinks for each KB dir", status: "pending", priority: "medium" }
])

---

Phase 1: Discovery + Analysis (Concurrent)

Mark "discovery" as in_progress.

Launch Parallel Explore Agents

Multiple Task calls in a single message execute in parallel. Results return directly.

// All Task calls in ONE message = parallel execution

Task(
  description="project structure",
  subagent_type="explore",
  prompt="Project structure: PREDICT standard patterns for detected language → REPORT deviations only"
)

Task(
  description="entry points",
  subagent_type="explore",
  prompt="Entry points: FIND main files → REPORT non-standard organization"
)

Task(
  description="conventions",
  subagent_type="explore",
  prompt="Conventions: FIND config files (.eslintrc, pyproject.toml, .editorconfig) → REPORT project-specific rules"
)

Task(
  description="anti-patterns",
  subagent_type="explore",
  prompt="Anti-patterns: FIND 'DO NOT', 'NEVER', 'ALWAYS', 'DEPRECATED' comments → LIST forbidden patterns"
)

Task(
  description="build/ci",
  subagent_type="explore",
  prompt="Build/CI: FIND .github/workflows, Makefile → REPORT non-standard patterns"
)

Task(
  description="test patterns",
  subagent_type="explore",
  prompt="Test patterns: FIND test configs, test structure → REPORT unique conventions"
)

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

# Measure project scale first
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)

Example spawning (all in ONE message for parallel execution):

// 500 files, 50k lines, depth 6, 15 large files → spawn additional agents
Task(
  description="large files",
  subagent_type="explore",
  prompt="Large file analysis: FIND files >500 lines, REPORT complexity hotspots"
)

Task(
  description="deep modules",
  subagent_type="explore",
  prompt="Deep modules at depth 4+: FIND hidden patterns, internal conventions"
)

Task(
  description="cross-cutting",
  subagent_type="explore",
  prompt="Cross-cutting concerns: FIND shared utilities across directories"
)
// ... more based on calculation

Main Session: Concurrent Analysis

While Task agents execute, main session does:

1. Bash Structural Analysis

# 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

2. Read Existing AGENTS.md

For each existing file found:
  Read(filePath=file)
  Extract: key insights, conventions, anti-patterns
  Store in EXISTING_AGENTS map

If --create-new: Read all existing first (preserve context) → then delete all → regenerate.

3. LSP Codemap (if available)

lsp_servers()  # Check availability

# Entry points (parallel)
lsp_document_symbols(filePath="src/index.ts")
lsp_document_symbols(filePath="main.py")

# Key symbols (parallel)
lsp_workspace_symbols(filePath=".", query="class")
lsp_workspace_symbols(filePath=".", query="interface")
lsp_workspace_symbols(filePath=".", query="function")

# Centrality for top exports
lsp_find_references(filePath="...", line=X, character=Y)

LSP Fallback: If unavailable, rely on explore agents + AST-grep.

Merge: bash + LSP + existing + Task agent results. Mark "discovery" as completed.

---

Phase 2: Scoring & Location Decision

Mark "scoring" as in_progress.

Scoring Matrix

Factor	Weight	High Threshold	Source
File count	3x	>20	bash
Subdir count	2x	>5	bash
Code ratio	2x	>70%	bash
Unique patterns	1x	Has own config	explore
Module boundary	2x	Has index.ts/init.py	bash
Symbol density	2x	>30 symbols	LSP
Export count	2x	>10 exports	LSP
Reference centrality	3x	>20 refs	LSP

Decision Rules

Score	Action
Root (.)	ALWAYS create
>15	Create AGENTS.md
8-15	Create if distinct domain
<8	Skip (parent covers)

Output

AGENTS_LOCATIONS = [
  { path: ".", type: "root" },
  { path: "src/hooks", score: 18, reason: "high complexity" },
  { path: "src/api", score: 12, reason: "distinct domain" }
]

Mark "scoring" as completed.

---

Phase 3: Generate AGENTS.md

Mark "generate" as in_progress.

Root AGENTS.md (Full Treatment)

# PROJECT KNOWLEDGE BASE

**Generated:** {TIMESTAMP}
**Commit:** {SHORT_SHA}
**Branch:** {BRANCH}

## OVERVIEW
{1-2 sentences: what + core stack}

## STRUCTURE
\`\`\`
{root}/
├── {dir}/    # {non-obvious purpose only}
└── {entry}
\`\`\`

## WHERE TO LOOK
| Task | Location | Notes |
|------|----------|-------|

## CODE MAP
{From LSP - skip if unavailable or project <10 files}

| Symbol | Type | Location | Refs | Role |

## CONVENTIONS
{ONLY deviations from standard}

## ANTI-PATTERNS (THIS PROJECT)
{Explicitly forbidden here}

## UNIQUE STYLES
{Project-specific}

## COMMANDS
\`\`\`bash
{dev/test/build}
\`\`\`

## NOTES
{Gotchas}

Quality gates: 50-150 lines, no generic advice, no obvious info.

Subdirectory AGENTS.md (Parallel)

Launch general agents for each location in ONE message (parallel execution):

// All in single message = parallel
Task(
  description="AGENTS.md for src/hooks",
  subagent_type="general",
  prompt="Generate AGENTS.md for: src/hooks
    - Reason: high complexity
    - 30-80 lines max
    - NEVER repeat parent content
    - Sections: OVERVIEW (1 line), STRUCTURE (if >5 subdirs), WHERE TO LOOK, CONVENTIONS (if different), ANTI-PATTERNS
    - Write directly to src/hooks/AGENTS.md"
)

Task(
  description="AGENTS.md for src/api",
  subagent_type="general",
  prompt="Generate AGENTS.md for: src/api
    - Reason: distinct domain
    - 30-80 lines max
    - NEVER repeat parent content
    - Sections: OVERVIEW (1 line), STRUCTURE (if >5 subdirs), WHERE TO LOOK, CONVENTIONS (if different), ANTI-PATTERNS
    - Write directly to src/api/AGENTS.md"
)
// ... one Task per AGENTS_LOCATIONS entry

Results return directly. Mark "generate" as completed.

---

Phase 4: Review & Deduplicate

Mark "review" as in_progress.

For each generated file:

• Remove generic advice
• Remove parent duplicates
• Trim to size limits
• Verify telegraphic style

Mark "review" as completed.

---

Phase 5: CLAUDE.md symlinks

Mark "symlinks" as in_progress after review completes.

Goal: In every directory where this workflow maintains AGENTS.md as the canonical knowledge file, CLAUDE.md must be a relative symlink to AGENTS.md (same content for Cursor rules vs Claude; single source of truth).

1. Discover targets — find all AGENTS.md under the repo (exclude node_modules, .git, vendored trees). For each …/AGENTS.md, the sibling …/CLAUDE.md should be -> AGENTS.md.
2. Skip intentional exceptions — If CLAUDE.md must differ from AGENTS.md (rare), leave as a regular file and note in the final report.
3. Replace — In each target directory: remove any existing CLAUDE.md file, then ln -sf AGENTS.md CLAUDE.md. Use /bin/rm -f CLAUDE.md (or command rm) if the shell aliases rm to something that breaks on symlinks (e.g. rimraf).
4. Verify — ls -la …/CLAUDE.md shows -> AGENTS.md; git stores mode 120000 for symlinks.

Mark "symlinks" as completed.

---

Final Report

=== index-knowledge Complete ===

Mode: {update | create-new}

Files:
  ✓ ./AGENTS.md (root, {N} lines)
  ✓ ./src/hooks/AGENTS.md ({N} lines)

Symlinks:
  ✓ ./CLAUDE.md -> AGENTS.md
  ✓ ./src/hooks/CLAUDE.md -> AGENTS.md

Dirs Analyzed: {N}
AGENTS.md Created: {N}
AGENTS.md Updated: {N}

Hierarchy:
  ./AGENTS.md
  └── src/hooks/AGENTS.md

---

Anti-Patterns

• Static agent count: MUST vary agents based on project size/depth
• Sequential execution: MUST parallel (multiple Task calls in one message)
• 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
• Verbose style: Telegraphic or die
• Duplicate CLAUDE.md: After generating AGENTS.md, do not leave a copied CLAUDE.md — symlink or editors drift apart