Codebase Knowledge Graph Q&A
Egonex-AI/Understand-Anything
Answers questions about a codebase by searching a prebuilt knowledge graph of its files, functions, classes and dependencies, not by rereading every source file.
Searches a codebase by meaning with the jbcontext CLI when you do not know which file or symbol holds the behavior you are looking for.
Install Semantic Code Search
$ npx skills add GitTools/GitVersion --skill context-search -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install GitTools/GitVersion context-search --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/GitTools/GitVersion.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.ai/skills/context-search .claude/skills/context-search && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "context-search" agent skill from https://github.com/GitTools/GitVersion/tree/main/.ai/skills/context-search into .claude/skills/context-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-search", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/GitTools/GitVersion/tree/main/.ai/skills/context-searchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add GitTools/GitVersion --skill context-search -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install GitTools/GitVersion context-search --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GitTools/GitVersion.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.ai/skills/context-search .agents/skills/context-search && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "context-search" agent skill from https://github.com/GitTools/GitVersion/tree/main/.ai/skills/context-search into .agents/skills/context-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-search", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GitTools/GitVersion --skill context-search -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install GitTools/GitVersion context-search --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GitTools/GitVersion.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.ai/skills/context-search .cursor/skills/context-search && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "context-search" agent skill from https://github.com/GitTools/GitVersion/tree/main/.ai/skills/context-search into .cursor/skills/context-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-search", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/GitTools/GitVersion.git --path .ai/skills/context-search--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add GitTools/GitVersion --skill context-search -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install GitTools/GitVersion context-search --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GitTools/GitVersion.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.ai/skills/context-search .gemini/skills/context-search && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "context-search" agent skill from https://github.com/GitTools/GitVersion/tree/main/.ai/skills/context-search into .gemini/skills/context-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-search", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install GitTools/GitVersion context-searchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add GitTools/GitVersion --skill context-search -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/GitTools/GitVersion.git skills-src && mkdir -p .github/skills && cp -r skills-src/.ai/skills/context-search .github/skills/context-search && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "context-search" agent skill from https://github.com/GitTools/GitVersion/tree/main/.ai/skills/context-search into .github/skills/context-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-search", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GitTools/GitVersion --skill context-search -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install GitTools/GitVersion context-search --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GitTools/GitVersion.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.ai/skills/context-search .opencode/skills/context-search && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "context-search" agent skill from https://github.com/GitTools/GitVersion/tree/main/.ai/skills/context-search into .opencode/skills/context-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-search", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
context-search- GitHub stars
- 3.1k
- Token cost
- ~465 tokens
- SKILL.md length
- 134 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Searches a codebase by meaning with the jbcontext CLI when you do not know which file or symbol holds the behavior you are looking for.
- Finding where a behavior is implemented when no symbol is named
- SKILL.md covers Usage, Query Tips and Examples
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Answering how a feature works in an unfamiliar repository
What it does
The skill wraps the jbcontext search command, which returns code snippets that match a description or a similar snippet rather than a keyword. It is meant as a single semantic starting point: run one broad search, open at least one returned file and read the code around it, and only then retry. A retry narrows the search with a path option, relative to the project root, using the directory of the best first hit.
Query tips favor descriptive phrases over single words, such as a function that validates user email addresses, plus context such as error-handling middleware with logging. The first query should name the feature, class, method or behavior from the task when there is one. The skill is not for cases where the file or symbol is already known, nor for git operations, builds, tests or reviewing a diff.
When your agent uses it
- Finding where a behavior is implemented when no symbol is named
- Answering how a feature works in an unfamiliar repository
- Locating code similar to a snippet you paste in
- Starting a bug investigation from a description of the symptom
Example prompts
- “Where does the authentication login flow live in this repo?”
- “Find code similar to this retry loop I pasted.”
- “How does the version calculation decide which commit to start from?”
Requirements
- The jbcontext CLI available in the project
What it can do on your machine
Read from SKILL.md and the folder at commit 92e2456. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Semantic Code Search loads about 465 tokens when it runs. Until then it costs about 135 tokens; SKILL.md has 134 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from GitTools/GitVersion at commit 92e2456, republished under its MIT licence (© GitTools). 134 words, ~465 tokens.
Download SKILL.mdSave it as
.claude/skills/context-search/SKILL.md (or your agent's skills folder).- name
- context-search
- description
- Semantic code search for discovering and understanding code by meaning rather than keywords. - Use this skill when you need to find code whose location you don't already know - e.g., when the task asks 'where is X', 'how does Y work', or describes behavior or intent without naming exact symbols. - When not to use: if you already know the relevant file, class, or symbol (use direct navigation or keyword search instead), or for non-code-discovery tasks such as git operations, builds, tests, or reviewing an existing diff.
- argument-hint
- query
Semantic Code Search
Use jbcontext search to find code snippets by meaning, not just keywords.
Use it as a single semantic bootstrap when the relevant file or subsystem is unknown. Do one broad search, open and inspect at least one returned file locally, and inspect nearby code in that same directory or subsystem before any retry. If that still does not identify the needed adjacent area, do a narrowed retry with jbcontext search -p <path> ... using the directory of the best first hit.
Usage
jbcontext search "<detailed and descriptive query>"
jbcontext search "<code snippet>" # find similar snippets
jbcontext search -p <path> "<query>" # <path> must be relative to the project rootQuery Tips
- Be descriptive: "function that validates user email addresses" > "email"
- Include context: "error handling middleware for HTTP requests with logging"
- Specify what you're looking for: "React component that renders a modal dialog"
- Make the first query specific to the issue's named feature, class, method, or behavior when available
Examples
# Find authentication-related code
jbcontext search "user authentication login flow"
# Narrow to specific directory
jbcontext search -p src/auth "JWT token validation"© GitTools, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .ai/skills/context-search of GitTools/GitVersion.
Open the folder on GitHubat commit 92e2456
Compare with similar skills
Semantic Code Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Semantic Code Search this skillGitTools/GitVersion | 3.1k | — | ~465 | Automated safety check: Pass | MIT | |
| Codebase Knowledge Graph Q&AEgonex-AI/Understand-Anything | 85k | 1 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Understand ExplainEgonex-AI/Understand-Anything | 85k | 1 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Repomix Codebase Exploreryamadashy/repomix | 29k | 1 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Project Onboarding Guide from Knowledge GraphEgonex-AI/Understand-Anything | 85k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Deepwiki Rssopaco/deepwiki-rs | 3.1k | — | ~748 | Automated safety check: Pass | MIT |
Similar skills
Understand Explain
Egonex-AI/Understand-Anything
Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.
Repomix Codebase Explorer
yamadashy/repomix
Packs a local or remote repository into a single AI-friendly file with the Repomix CLI, then reads and searches that output to explain structure, find patterns or report metrics.
Project Onboarding Guide from Knowledge Graph
Egonex-AI/Understand-Anything
Writes an onboarding guide for new team members from a project's existing knowledge graph, after checking that the graph still matches the current commit.
Deepwiki Rs
sopaco/deepwiki-rs
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation.
GitDiagram Repository Overview
ahmedkhaleel2004/gitdiagram
Explains the architecture of a public GitHub repository through GitDiagram: how the code is organized, the main components with paths, and a Mermaid diagram.
More from GitTools/GitVersion
GitVersion .NET Development
GitTools/GitVersion
Gives repository-specific .NET guidance for GitVersion: build and test commands, central package management, project layout and coding conventions.
Related
Categories
Questions about Semantic Code Search
What does Semantic Code Search do?
Searches a codebase by meaning with the jbcontext CLI when you do not know which file or symbol holds the behavior you are looking for. The skill wraps the jbcontext search command, which returns code snippets that match a description or a similar snippet rather than a keyword. It is meant as a single semantic starting point: run one broad search, open at least one returned file and read the code around it, and only then retry.
When should I use Semantic Code Search?
Semantic Code Search fits situations like: finding where a behavior is implemented when no symbol is named; answering how a feature works in an unfamiliar repository; locating code similar to a snippet you paste in; starting a bug investigation from a description of the symptom.
How do I install Semantic Code Search in Claude Code?
Run `npx skills add GitTools/GitVersion --skill context-search -a claude-code`. Or copy the skill folder (.ai/skills/context-search in GitTools/GitVersion) into .claude/skills/context-search in your project. Claude Code loads it when a task matches its description.
How do I install Semantic Code Search in Codex?
Run `npx skills add GitTools/GitVersion --skill context-search -a codex`. Or copy the skill folder (.ai/skills/context-search in GitTools/GitVersion) into .agents/skills/context-search in your project. Codex loads it when a task matches its description.
Can I use Semantic Code Search in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GitTools/GitVersion --skill context-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/context-search, .gemini/skills/context-search, .github/skills/context-search and .opencode/skills/context-search in your project.
What does Semantic Code Search need to run?
SKILL.md names no scripts, command-line tools or credentials: Semantic Code Search is instructions for the agent only. Our summary lists: The jbcontext CLI available in the project.
Does Semantic Code Search access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Semantic Code Search safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Semantic Code Search use?
Semantic Code Search is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Semantic Code Search use?
About 465 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Semantic Code Search?
Skills that share tags, products or a category with Semantic Code Search: Codebase Knowledge Graph Q&A (Egonex-AI/Understand-Anything, 85k stars), Understand Explain (Egonex-AI/Understand-Anything, 85k stars), Repomix Codebase Explorer (yamadashy/repomix, 29k stars) and Project Onboarding Guide from Knowledge Graph (Egonex-AI/Understand-Anything, 85k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Semantic Code Search?
GitTools (a GitHub organization) maintains it in GitTools/GitVersion, which has 3,149 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 2026.
Source: GitTools/GitVersion on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.