analyze-docs

A command for reviewing a project's documentation and its relationship to the code and architecture.

In plain words
What is it for?
It helps assess CLAUDE.md and AGENTS.md files, architecture documentation, roadmap progress, AI documentation coverage, and differences between plans and implementation.
Why use it?
It creates an inventory and highlights missing, stale, inconsistent, or misaligned guidance for developers and AI agents.

Command for Claude Code

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.

agentmods
npx agentmods add commands/consiliency/code-index-mcp/analyze-docs
Clone the repo
git clone --depth 1 https://github.com/Consiliency/Code-Index-MCP

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,424 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02424
Opus 5 $0.00000 $0.01212
Sonnet 5 $0.00000 $0.00485
Haiku 4.5 $0.00000 $0.00242

Measured 2d ago against content hash 1a9d7de43223, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-docs 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 2d 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.

.claude/commands/analyze-docs.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

analyze-docs

Perform comprehensive documentation analysis optimized for AI agent development workflows. Creates markdown-table-of-contents.md with architectural alignment insights and complexity annotations.

PRIMARY_ANALYSIS_OBJECTIVES

  1. Create comprehensive markdown file inventory with AI agent context annotations
  2. Analyze CLAUDE.md → AGENTS.md migration needs and custom guidance detection
  3. Map C4 architecture levels (DSL L1-3 and PlantUML L4) with alignment status
  4. Assess ROADMAP.md implementation progress with complexity scoring
  5. Detect codebase-architecture divergences for governance tracking
  6. Evaluate /ai_docs staleness and framework coverage
  7. Analyze AI platform guidance consistency across CLAUDE.md, AGENTS.md, and Cursor rules

EXECUTION_SEQUENCE

PHASE_1: INTELLIGENT_FILE_DISCOVERY_AND_CLASSIFICATION

# Discover all documentation with context
echo "=== DOCUMENTATION DISCOVERY ==="
find . -name "*.md" -type f | while read file; do
    # Classify by AI agent relevance
    if [[ "$file" == *"CLAUDE.md"* ]] || [[ "$file" == *"AGENTS.md"* ]]; then
        echo "AI_AGENT_CONTEXT: $file"
    elif [[ "$file" == *"README.md"* ]]; then
        echo "HUMAN_CONTEXT: $file"
    else
        echo "MIXED_CONTEXT: $file"
    fi
done

# Discover architecture files with C4 level detection
echo "=== ARCHITECTURE DISCOVERY ==="
find . -name "*.dsl" -type f | while read file; do
    if grep -q "workspace\|container\|component" "$file"; then
        echo "STRUCTURIZR_DSL (C4 L1-3): $file"
    fi
done

find . -name "*.puml" -o -name "*.plantuml" | while read file; do
    echo "PLANTUML (C4 L4): $file"
done

PHASE_2: CLAUDE_MD_MIGRATION_ANALYSIS

# Analyze CLAUDE.md files for custom guidance
echo "=== CLAUDE.MD MIGRATION ANALYSIS ==="
find . -name "CLAUDE.md" -type f | while read file; do
    echo "Analyzing: $file"
    
    # Check if it's a pure pointer
    if grep -q "refer to.*AGENTS.md" "$file" && ! grep -q "^[^#]" "$file"; then
        echo "STATUS: Pure pointer (compliant)"
    else
        echo "STATUS: Contains custom guidance (needs migration)"
        # Extract custom content for migration
        grep -v "refer to.*AGENTS.md" "$file" | grep -v "^#.*AGENTS.md" > "${file}.custom"
    fi
done

Read the full file on GitHub · 272 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. 2d ago First seen · 272 lines · 0 tokens per session scan A 1a9d7de43223

Subscribe to this mod's changes

analyze-docs is a command published in the GitHub repository Consiliency/Code-Index-MCP (57 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,424 tokens. 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 2026-08-30.