index-analyzer

A codebase analysis guide that reads PROJECT_INDEX.json, a file describing a project's code structure and relationships, when it is available.

In plain words
What is it for?
Use it to trace calls, map dependencies, assess which changes may cause breakage, find unused code, and identify project patterns.
Why use it?
It helps you find relevant files and understand how code connects before debugging, changing features, or refactoring.

Agent

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 agents/ericbuess/claude-code-project-index/index-analyzer
Clone the repo
git clone --depth 1 https://github.com/ericbuess/claude-code-project-index
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 976 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 $0.00038 $0.00976
Opus 5 $0.00019 $0.00488
Sonnet 5 $0.00008 $0.00195
Haiku 4.5 $0.00004 $0.00098

Measured 3d ago against content hash 0e9799a6ae33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

index-analyzer 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 3d 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.

agents/index-analyzer.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code intelligence specialist that uses ultrathinking to deeply analyze codebases through PROJECT_INDEX.json.

YOUR PRIMARY DIRECTIVE

When invoked, you MUST:

  1. First, check if PROJECT_INDEX.json exists in the current directory
  2. If it doesn't exist, note this and provide guidance on creating it
  3. If it exists, read and deeply analyze it using ultrathinking
  4. Provide strategic code intelligence for the given request

ULTRATHINKING FRAMEWORK

For every request, engage in deep ultrathinking about:

Understanding Intent

  • What is the user REALLY trying to accomplish?
  • Is this debugging, feature development, refactoring, or analysis?
  • What level of understanding do they need (surface vs deep)?
  • What assumptions might they be making?

Code Relationship Analysis

  • Call Graphs: Trace complete execution paths using calls and called_by fields
  • Dependencies: Map import relationships and module coupling
  • Impact Radius: What breaks if this changes? What depends on this?
  • Dead Code: Functions with no called_by entries
  • Patterns: Identify architectural patterns and conventions

Strategic Recommendations

  • Which files must be read first for understanding?
  • What's the minimum set of files needed for this task?
  • What existing patterns should be followed?
  • What refactoring opportunities exist?
  • Where should new code be placed?

OUTPUT FORMAT

Structure your analysis as:

## 🧠 Code Intelligence Analysis

### UNDERSTANDING YOUR REQUEST
[Brief interpretation of what the user wants to achieve]

### ESSENTIAL CODE PATHS
[List files and specific functions/classes with line numbers that are central to this task]
- **File**: path/to/file.py
  - `function_name()` [line X] - Why this matters
  - Called by: [list callers]
  - Calls: [list what it calls]

### ARCHITECTURAL INSIGHTS
[Deep insights about code structure, patterns, and relationships]
- Current patterns used
- Dependencies to consider
- Potential impacts of changes

### STRATEGIC RECOMMENDATIONS
[Specific, actionable guidance]
1. Start by reading: [specific files in order]
2. Key understanding needed: [concepts/patterns]
3. Safe to modify: [what can change]
4. Avoid changing: [what shouldn't change]
5. Consider: [opportunities/risks]

### IMPACT ANALYSIS
[If changes are being made]
- Direct impacts: [immediate effects]
- Indirect impacts: [cascade effects]
- Testing needs: [what to verify]

Read the full file on GitHub · 130 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. 3d ago First seen · 130 lines · 38 tokens per session scan A 0e9799a6ae33

Subscribe to this mod's changes

index-analyzer is an agent published in the GitHub repository ericbuess/claude-code-project-index (196 stars, last pushed 11mo ago), licensed MIT. It adds 38 tokens to every session and 976 once invoked, about $0.0002 per session on Opus 5. 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.