Provides graph-backed code intelligence and repository mapping for advanced codebase navigation.
Install
mkdir -p .claude/skills/code-explorer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12779" && unzip -o skill.zip -d .claude/skills/code-explorer && rm skill.zipInstalls to .claude/skills/code-explorer
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use Code Explorer / Code Explorer CLI as Codex's code-intelligence layer before broad manual search. Use when answering code questions, mapping repositories such as /home/patrice/code-buddy, tracing symbols, call graphs, impact, dependencies, MCP setup, documentation generation, or when improving TypeScript/JavaScript/C#/Rust graph accuracy.Key capabilities
- →Analyze target repositories for code understanding
- →Check or create code indexes incrementally
- →Query code graphs for specific information
- →Trace symbol usage and dependencies
- →Analyze impact of code changes in both directions
- →Generate documentation for code structure
How it works
This skill indexes code repositories to create a graph-backed map of the code, allowing for deep queries about code structure, symbol usage, and dependencies. It identifies the target repository, checks or creates an index, and then executes graph queries.
Inputs & outputs
When to use code-explorer
- →Map repository structure
- →Trace symbol usage and dependencies
- →Analyze impact of code changes
About this skill
Code Explorer CLI Skill
Use Code Explorer first for repository understanding, then read exact files to verify details. This skill is especially important for Code Buddy (/home/patrice/code-buddy) because Patrice wants Claude, Codex, and Code Buddy to share the same graph-backed map of the code.
Binary
From this repository (/home/patrice/DEV/code-explorer-rs), prefer:
cargo run -p code-explorer-cli -- <command>
After a release build, use:
./target/release/code-explorer <command>
Use code-explorer <command> only when the binary is known to be on PATH.
Default Workflow
- Identify the target repository path.
- Current Code Explorer repo:
/home/patrice/DEV/code-explorer-rs - Canonical Linux Code Buddy repo:
/home/patrice/code-buddy - Older DEV copy:
/home/patrice/DEV/code-buddy
- Current Code Explorer repo:
- Check or create the index:
- From Code Explorer, run
cargo run -p code-explorer-cli -- analyze <target-repo> --skip-git --incremental. - After a release build, run
(cd <target-repo> && /home/patrice/DEV/code-explorer-rs/target/release/code-explorer status). - Use
--forcewhen validating resolver changes or when stale graph output is suspected.
- From Code Explorer, run
- Start with graph queries:
cargo run -p code-explorer-cli -- query "authentication flow" --repo <target-repo> --limit 10cargo run -p code-explorer-cli -- context <symbol> --repo <target-repo>cargo run -p code-explorer-cli -- impact <symbol> --repo <target-repo> --direction bothcargo run -p code-explorer-cli -- trace-files <symbol> --path <target-repo> --depth 3 --json
- Read precise files returned by Code Explorer before editing or making claims.
- If graph output conflicts with source code, trust source code and note the graph issue.
TypeScript / JavaScript Graph Checks
For TS/JS resolver work, always run an ambiguity reproducer before broad validation:
GN="cargo run -p code-explorer-cli --"
rm -rf /tmp/ambi && mkdir -p /tmp/ambi
printf 'export function foo() { return 1; }\n' > /tmp/ambi/a.ts
printf 'export function foo() { return 2; }\n' > /tmp/ambi/c.ts
printf 'import { foo } from "./a.js";\nexport function load() { return foo(); }\n' > /tmp/ambi/b.ts
$GN analyze /tmp/ambi --skip-git --force
grep CALLS /tmp/ambi/.codeexplorer/csv/CodeRelation.csv | grep foo
Expected result: load -> a.ts:foo with reason named-import or another import-scoped reason, not global.
Also test the dynamic form:
export async function load() {
const { foo } = await import("./a.js");
return foo();
}
Code Buddy Validation
When a change is meant to help Code Buddy:
cargo run -p code-explorer-cli -- analyze /home/patrice/code-buddy/src --skip-git --force
cargo run -p code-explorer-cli -- query "autonomous code runner" --repo /home/patrice/code-buddy/src --limit 10
cargo run -p code-explorer-cli -- context runTurnLoop --repo /home/patrice/code-buddy/src
Track CALLS confidence by inspecting .codeexplorer/csv/CodeRelation.csv under the indexed repo. A useful resolver improvement should reduce low-confidence global CALLS edges and increase named-import / import-scoped edges.
MCP Setup
For Claude Code or a project-local consumer, install the MCP server from the target project directory:
cd <target-repo>
/home/patrice/DEV/code-explorer-rs/target/release/code-explorer mcp-install --scope project
If no release binary exists, build it first:
cd /home/patrice/DEV/code-explorer-rs
cargo build --release -p code-explorer-cli
Guardrails
- Do not use Code Explorer output as the sole authority for code edits; verify exact source.
- Do not run destructive git commands in indexed repositories.
- Use
--skip-gitfor synthetic fixtures and partial source directories. - For resolver work, avoid changing validated C#/ASP.NET/EDMX behavior unless the task explicitly targets it.
When not to use it
- →Code Explorer output is the sole authority for code edits
- →The task involves destructive git commands in indexed repositories
- →The task requires changing validated C#/ASP.NET/EDMX behavior
Limitations
- →Code Explorer output should not be the sole authority for code edits
- →Destructive git commands should not be run in indexed repositories
- →The `--skip-git` option is used for synthetic fixtures and partial source directories
How it compares
This skill provides a structured, graph-based approach to understanding codebases and their relationships, offering a more detailed and interconnected view than simple file searches or manual code inspection.
Compared to similar skills
code-explorer side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| code-explorer (this skill) | 0 | 1mo | Review | Intermediate |
| solana-dev | 0 | 4mo | No flags | Beginner |
| deepwiki-rs | 25 | 9mo | Review | Intermediate |
| react-component-patterns | 3 | 1mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
solana-dev
solanabr
Unified skill hub for Solana development. Routes to external submodule skills (solana-foundation, sendai, solana-game, trailofbits, cloudflare, qedgen, colosseum) and local skills. Progressive disclosure — read only what you need.
deepwiki-rs
sopaco
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.
react-component-patterns
HoangNguyen0403
Modern React component architecture and composition patterns.
vercel-architecture-variants
jeremylongshore
Execute choose and implement Vercel validated architecture blueprints for different scales. Use when designing new Vercel integrations, choosing between monolith/service/microservice architectures, or planning migration paths for Vercel applications. Trigger with phrases like "vercel architecture", "vercel blueprint", "how to structure vercel", "vercel project layout", "vercel microservice".
ai-code
arcasilesgroup
Writes production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review. Trigger for 'implement this', 'write the code for', 'add X to Y', 'build this function', 'make this work'. Not for tests; use /ai-test inst
harness-boundary
zkp442910864
Harness 工程边界约束与变更评估。Use when: 评估代码变更影响范围、确认安全边界、检查工程规范合规性、审查变更风险等级。