# Map large codebases with focused symbol search

Large repositories can overwhelm code exploration and consume limited context. This skill builds a local symbol index so you can retrieve targeted code and preserve project knowledge.

## Install

```bash
npx skillstore add chipflow/context-tools
```

## Metadata

- Status: approved
- Slug: chipflow-context-tools
- Skillstore revision: r3
- Version status: missing
- Tree hash: b63255863cf22984b0457ebfee8e01a76f3a17526f5faa0e8108751e4fe43bd8
- Author: ChipFlow
- GitHub username: ChipFlow
- License: MIT
- Repository: https://github.com/ChipFlow/claude-context-tools/tree/main/
- Ref: c68df504887c54bf71d2d467a1fbebde49467868
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: confirmation\_required
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: network, external\_commands, filesystem, env\_access
- Quality score: 76
- Public page: https://skillstore.pages.dev/skills/chipflow-context-tools
- Manifest: https://skillstore.pages.dev/api/skills/chipflow-context-tools/manifest

## Capabilities

- Indexes Python, Rust, and C\+\+ symbols into a local repository map.
- Searches indexed functions, classes, methods, and types through MCP tools.
- Retrieves indexed symbol content and file-level symbol lists.
- Detects similar code patterns with fuzzy matching.
- Tracks indexing status and supports manual reindexing.
- Stores project narratives, learnings, and cross-session goals in Claude directories.

## Use Cases

- Navigate an unfamiliar service: Find the relevant classes and functions before changing a large existing codebase.
- Prepare an implementation plan: Locate related symbols and dependencies to create a focused technical plan.
- Preserve team knowledge: Maintain project narratives, learnings, and goals across Claude Code sessions.

## Prompt Templates

### Find a symbol

```
Find the symbol named AuthService and show its signature, location, and related methods.
```

### Explore a module

```
List the indexed symbols in src/api.py. Summarize each public function in one sentence.
```

### Trace an implementation

```
Search for symbols related to payment retries. Identify the main flow and the files I should review.
```

### Plan a safe change

```
Use the repository map to find all symbols affected by adding a cache to the config loader. Propose a change plan and test scope.
```

## Limitations

- Language indexing is limited to Python, Rust, and C\+\+.
- MCP symbol tools require the plugin server to load and the repository to be indexed.
- Initial indexing can take time on large repositories.
- Narrative generation requires an Anthropic API key and supported Claude tooling.

## Best Practices

- Use symbol search before broad text search when you know a code identifier.
- Wait for initial indexing to complete before relying on symbol results.
- Review generated narratives and learnings before treating them as team documentation.

## Anti Patterns

- Do not use the index as the only source of truth for unindexed languages or generated files.
- Do not store secrets in project narratives, learnings, or goals.
- Do not assume a symbol search result proves runtime behavior without reviewing the source.

## Security Audit

- Audited at: 2026-07-18T10:24:18.049\+00:00
- Summary: All 94 static findings are false positives caused by documentation, metadata, and static assets. The reviewed material describes local indexing and optional tooling, with no evidence of credential exfiltration, malicious persistence, prompt injection, or executable command injection.

## Stats

- Views: 476
- Downloads: 18
- Favorites: 0
- Popularity score: 0