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.
git clone --depth 1 https://github.com/ericbuess/claude-code-project-indexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/ericbuess/claude-code-project-index/index-analyzer)<a href="https://agentmods.dev/agents/ericbuess/claude-code-project-index/index-analyzer"><img src="https://agentmods.dev/badge/agents/ericbuess/claude-code-project-index/index-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ericbuess/claude-code-project-index/index-analyzer"><img src="https://agentmods.dev/badge/agents/ericbuess/claude-code-project-index/index-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00976 |
| Opus 5.5 | $0.00015 | $0.00390 |
| Sonnet 5.5 | $0.00008 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00098 |
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 1mo 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.
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:
- First, check if PROJECT_INDEX.json exists in the current directory
- If it doesn't exist, note this and provide guidance on creating it
- If it exists, read and deeply analyze it using ultrathinking
- 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
callsandcalled_byfields - Dependencies: Map import relationships and module coupling
- Impact Radius: What breaks if this changes? What depends on this?
- Dead Code: Functions with no
called_byentries - 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]
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.
- 1mo ago First seen · 130 lines · 38 tokens per session scan A 0e9799a6ae33
index-analyzer is an agent published in the GitHub repository ericbuess/claude-code-project-index (197 stars, last pushed 1y ago), licensed MIT. It adds 38 tokens to every session and 976 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.