Skip to content
Back to skills

Use Cli Codegraph

ASecurity

Symbol-level code structure queries via codegraph CLI. Callers, callees, change impact, and symbol source trails.

  • 12 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 24, 2026
ai-agentsbashnoderails

Works with

  • cli

Security analysis

A100/100

Scanned September 24, 2026

npx -y skills add thkt/dotclaude --skill use-cli-codegraph --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Use Cli Codegraph?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Use Cli Codegraph
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/thkt-use-cli-codegraph-dotclaude/badge)](https://www.skillsdirectory.com/skills/thkt-use-cli-codegraph-dotclaude)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: use-cli-codegraph
description: Symbol-level code structure queries via codegraph CLI. Callers, callees, change impact, and symbol source trails.
when_to_use: who calls this, what breaks if I change X, impact analysis, callers, callees, call graph, symbol definition, code structure navigation, 影響範囲, 呼び出し元, 呼び出し先, 構造把握, 変更波及, dependency trace, 誰が呼んでいる
allowed-tools: Bash(codegraph:*) Read
user-invocable: false
---

# use-cli-codegraph

## When to use

Structural queries only. Route symbol-level structure questions like who calls X or what breaks to codegraph, and keep free-text content search on Grep / Explore.

| Question                                | Tool                                      |
| --------------------------------------- | ----------------------------------------- |
| What breaks if I change X / who calls X | codegraph; Grep cannot trace structure    |
| Symbol definition + caller/callee trail | codegraph node / explore                  |
| Tests affected by changed files         | codegraph affected                        |
| Free-text or string content search      | Grep / Explore; codegraph is symbol-level |
| Repo without a `.codegraph` index       | Grep / Explore, or prompt to init         |

## Commands

| Purpose                            | Command                         |
| ---------------------------------- | ------------------------------- |
| Change impact (what breaks)        | `codegraph impact <symbol>`     |
| Callers                            | `codegraph callers <symbol>`    |
| Callees                            | `codegraph callees <symbol>`    |
| Symbol source + call trail         | `codegraph node <name>`         |
| Explore area (source + call paths) | `codegraph explore <query...>`  |
| Symbol search                      | `codegraph query <search>`      |
| Tests affected by changes          | `codegraph affected [files...]` |
| Index status                       | `codegraph status`              |

## Prerequisites

| Item      | Detail                                                                                                                          |
| --------- | ------------------------------------------------------------------------------------------------------------------------------- |
| index     | `.codegraph/` required. Run `codegraph init` once per repo. If absent, ask whether to init and stop. Do not create it silently  |
| freshness | `codegraph status` shows up to date. Run `codegraph sync` after large changes. The watcher daemon keeps it current when running |
| binary    | Installed as a bun global. On EPERM during install / upgrade, prefix `npm_config_cache=$TMPDIR/cg` to work around it            |

## The help output is authoritative

Options, output format and exit codes live in `codegraph --help` and `codegraph <subcommand> --help`. Where help and memory differ, help is right.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.