ADK-Rust
← Skill registry
Developer workflowsPublic skills

Code Search & Navigation

Code intelligence for AI agents — semantic search, symbol lookup, call graphs, dependency mapping, blast radius analysis, and ownership resolution via mcp-code-search.

Open the skill source Read the official guide ↗

What this skill teaches

A reusable playbook for a specific kind of work.

An MCP server tells an agent which actions are available. A skill adds the judgment around those actions: how to recognize the job, which sequence to follow, what to avoid, and how to decide that the result is complete.

Orchestrate code intelligence — semantic search, symbol lookup, call graphs, dependency graphs, code ownership, and context packs. Use when finding code definitions, understanding call chains, mapping dependencies, identifying code owners, or building context for changes.

Architecture

How Code Search & Navigation guides an ADK-Rust agent.

The skill stays readable and portable because it contains instructions rather than service credentials or business data. ADK-Rust supplies it to the agent, the agent chooses from its reviewed tool boundary, and the connected MCP server performs the authenticated operation.

01

User request

The agent receives a goal expressed in ordinary language.

02

Code Search & Navigation skill

Matches intent, supplies the decision guide, and narrows the tool boundary.

03

ADK-Rust agent

Plans the workflow and streams each meaningful step through the runtime.

04

mcp-code-search

Executes authenticated operations against the system that owns the capability.

05

Verified result

The skill's completion rules shape the evidence returned to the user.

Portable instructions: SKILL.md · Capability boundary: mcp-code-search · Allowed tools: 8

Decision guide

How the agent turns a request into the right action.

These routes come directly from the skill instructions. They help the model recognize intent and select a focused tool or workflow instead of improvising across the entire capability surface.

01

"find", "where is", "search code"?

semantic_search

02

"definition", "what is", "symbol"?

lookup_symbol / explain_symbol

03

"who calls", "callers", "call graph"?

call_graph

04

"depends on", "dependency"?

dependency_graph

05

"who owns", "reviewer", "owner"?

codeowners

06

"context", "all files for"?

context_pack

07

"references", "usages", "used where"?

find_references

Proven workflows

Repeatable sequences for useful outcomes.

A workflow joins several tool calls into a task the user actually recognizes. The skill explains the sequence and the intended result while ADK-Rust streams the agent's progress through the shared runtime.

011 calls

Find Code

Semantic search across repos

022-3 calls

Understand Symbol

Definition + call graph + owners

032-3 calls

Blast Radius

Impact analysis before changes

041 calls

Build Context

All files needed for a task

Tool boundary

The skill may use 8 documented tools.

This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-code-search retains responsibility for authentication, validation, and the connected system.

semantic_search
lookup_symbol
find_references
call_graph
dependency_graph
codeowners
context_pack
explain_symbol

Working rules

What the agent should do.

  • Include file paths and line numbers in all results
  • Show blast radius before recommending changes
  • Route reviews to code owners

Operating boundaries

What the agent should avoid.

  • Review the complete SKILL.md before enabling this skill for production work.

Install and connect

Add the skill beside the capability it expects.

Install the repository where your ADK-Rust skill loader can discover it, connect mcp-code-search, and confirm the declared tools are available before asking the agent to use the workflow.

Install the skill
git clone https://github.com/zavora-ai/skill-code-search-navigation.git \
  ~/.skills/skills/code-search-navigation
ADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("code-search-navigation").await?;

let agent = LlmAgentBuilder::new("agent")
    .instruction(skill.instructions())
    .tools(skill.allowed_tools(toolset)?)
    .build()?;

The repository's compatibility statement: Requires mcp-code-search server connected.

Official documentation

Read the complete skill package.

The repository remains authoritative for its exact instructions, examples, helper scripts, assets, MCP requirements, license, and later updates.

Overview ↗README.mdSkill instructions ↗SKILL.mdCross Mcp Workflows ↗references/cross-mcp-workflows.mdExamples ↗references/examples.mdTool Sequences ↗references/tool-sequences.mdBlast Radius ↗scripts/blast_radius.pySearch Results ↗assets/search-results.md

Keep exploring

More in developer workflows.

Browser AutomationWeb operations for AI agents — read pages, extract data, take screenshots, interact with forms, and scrape structured content via headless Chromium.17 allowed toolsCI/CD Pipeline ManagementPipeline operations for AI agents — monitor builds, debug failures from logs, trigger safe deployments, and manage release gates via mcp-cicd.8 allowed toolsComputer UseDesktop automation for AI agents — screenshot, click, type, scroll, accessibility trees, form filling, menu navigation, scripts (AppleScript/JXA/PowerShell), app/window management. 49 tools.50 allowed tools

Source record

Repository metadata for this skill entry.

View public repository ↗
License
Apache-2.0
Allowed tools
8
References
3
Revision
983ea87d4b08
Updated
May 31, 2026