Agent skill

Code Explore

by sd0xdev in sd0xdev/sd0x-harness

Pure Claude code investigation. An agent skill from sd0xdev/sd0x-harness.

MITAuto-check passedDevelopment

Install Code Explore

skills CLI
$ npx skills add sd0xdev/sd0x-harness --skill code-explore -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sd0xdev/sd0x-harness code-explore --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sd0xdev/sd0x-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/code-explore .claude/skills/code-explore && rm -rf skills-src

Use ~/.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/

Facts

Skill name
code-explore
GitHub stars
192
Token cost
~1.5k tokens
SKILL.md length
166 words
Files
2 (incl. references)
Skills in repo
91
Repo updated
First seen
Licence
MIT

At a glance

Pure Claude code investigation. An agent skill from sd0xdev/sd0x-harness.

  • : tracing execution paths
  • SKILL.md covers Trigger, When to Use, When NOT to Use and Workflow, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Understanding architecture

What it does

Code Explore is an agent skill from sd0xdev/sd0x-harness. Pure Claude code investigation. Use when: tracing execution paths, understanding architecture, diagnosing issues. Not for: dual-perspective review (use code-investigate), code review (use codex-code-review). Output: analysis report with findings.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/search-patterns.md`).

It sits in Development, covering Code review. The repository describes itself as: The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and… The licence is MIT.

When your agent uses it

  • : tracing execution paths
  • Understanding architecture
  • Diagnosing issues

Example prompts

  • “/code-explore”

Requirements

  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash(ls:*), Bash(find:*)

What it can do on your machine

Read from SKILL.md and the folder at commit c9a2036. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Bash(ls:*)
    • Bash(find:*)

    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 markdown).

    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

Code Explore loads about 1.5k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 166 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

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 sd0xdev/sd0x-harness at commit c9a2036, republished under its MIT licence (© sd0xdev). 166 words, ~1,454 tokens.

Download SKILL.mdSave it as .claude/skills/code-explore/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
code-explore
description
Pure Claude code investigation. Use when: tracing execution paths, understanding architecture, diagnosing issues. Not for: dual-perspective review (use code-investigate), code review (use codex-code-review). Output: analysis report with findings.
allowed-tools
Read, Grep, Glob, Bash(ls:*), Bash(find:*)
context
fork

Code Explore Skill

Trigger

  • Keywords: code explore, code investigation, research code, trace code, feature understanding, quick investigation, code exploration

When to Use

  • Quickly understand how a feature works
  • Trace execution paths / data flow
  • Diagnose problem root causes
  • No dual confirmation needed (no Codex cross-validation)

When NOT to Use

ScenarioAlternative
Need dual confirmation/code-investigate (Claude + Codex)
Git history tracking/git-investigate
System verification/feature-verify
Code review/codex-review-fast

Workflow

┌──────────────────────────────────────────────────────────┐
│ Phase 1: Locate Entry Point                                │
├──────────────────────────────────────────────────────────┤
│ 1. Grep keywords -> find related files                     │
│ 2. Identify entry points (Controller / Service / Provider) │
│ 3. Build file list                                         │
└──────────────────────────────────────────────────────────┘
                          ↓
┌──────────────────────────────────────────────────────────┐
│ Phase 2: Trace Path                                        │
├──────────────────────────────────────────────────────────┤
│ 1. Start from entry point, Read                            │
│ 2. Identify dependencies -> continue tracing               │
│ 3. Map call chain (A -> B -> C)                            │
└──────────────────────────────────────────────────────────┘
                          ↓
┌──────────────────────────────────────────────────────────┐
│ Phase 3: Understand Logic                                  │
├──────────────────────────────────────────────────────────┤
│ 1. What is the core logic?                                 │
│ 2. How does data flow?                                     │
│ 3. Error handling mechanisms?                              │
│ 4. Key decision points?                                    │
└──────────────────────────────────────────────────────────┘
                          ↓
┌──────────────────────────────────────────────────────────┐
│ Phase 4: Output Report                                     │
├──────────────────────────────────────────────────────────┤
│ 1. Architecture overview (diagram / table)                 │
│ 2. Key files list                                          │
│ 3. Execution flow                                          │
│ 4. Findings / notes                                        │
└──────────────────────────────────────────────────────────┘

Search Strategy

TargetStrategy
Feature entryGrep "export class.*Controller" / Grep "@Get|@Post"
Service layerGrep "export class.*Service"
Provider layerGlob "src/provider/**/*.ts"
ConfigurationRead {CONFIG_FILE}
Data modelsGlob "src/model/**/*.ts"

Output Format

markdown
## Investigation Report: {Topic}

### Architecture Overview

{ASCII or Mermaid diagram}

### Key Files

| File              | Responsibility |
| ----------------- | -------------- |
| `path/to/file.ts` | Description   |

### Execution Flow

1. {Step 1}
2. {Step 2}
3. ...

### Data Flow

{Describe how data flows}

### Findings

- {Important finding 1}
- {Important finding 2}

### Notes

- {Potential issue / edge case}

Verification

  • Entry points identified and listed
  • Execution flow traced end-to-end
  • Key files table includes all relevant files
  • Findings section has actionable insights

References

  • references/search-patterns.md — Common search patterns for codebase exploration (read when building search strategy)

Examples

Feature Understanding
Input: Investigate how user data queries work
Phase 1: Grep "balance" -> find UserService, UserController
Phase 2: Controller -> Service -> Provider call chain
Phase 3: Understand query + cache mechanism
Phase 4: Output report + flow diagram
Problem Diagnosis
Input: Why does this API sometimes return empty?
Phase 1: Grep "getData" + "cache" -> related files
Phase 2: Trace data retrieval path
Phase 3: Identify fallback logic + timeout handling
Phase 4: List possible causes + recommendations
Architecture Understanding
Input: What is the overall architecture of the user module?
Phase 1: Glob "src/**/*user*" -> list all related files
Phase 2: Identify layer relationships (Controller -> Service -> Provider)
Phase 3: Understand each layer's responsibilities
Phase 4: Output architecture diagram + module description

Difference from code-investigate

Dimensioncode-explorecode-investigate
SpeedFast (single view)Slow (dual view)
ConfirmationSingle perspectiveCross-validation
ToolsPure ClaudeClaude + Codex
Use caseQuick investigationImportant decisions

© sd0xdev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/code-explore of sd0xdev/sd0x-harness.

  • SKILL.md
  • references/search-patterns.md

Open the folder on GitHubat commit c9a2036

Compare with similar skills

Code Explore 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.

Code Explore compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Explore this skillsd0xdev/sd0x-harness192—~1.5kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow156k—~3.5kAutomated safety check: NotesMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything85k1 repos~1.4kAutomated safety check: PassMIT
Mole Bug Patternstw93/Mole69k—~2kAutomated safety check: PassGPL-3.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    156k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check: notes
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    85k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    69k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed

More from sd0xdev/sd0x-harness

All 91 skills in this repo
  • Adr

    sd0xdev/sd0x-harness

    Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as docs/features/<feature/adr-<NNN-<title.md with a 3-digit zero-padded…

    192 GitHub stars~4.8k tokensUpdated yesterday
    Auto-check passed
  • Load PR Review

    sd0xdev/sd0x-harness

    Load GitHub PR review comments into AI session — analyze, triage, plan.

    192 GitHub stars~4.4k tokensUpdated yesterday
    Auto-check passed
  • Next Step

    sd0xdev/sd0x-harness

    Change-aware next step advisor. An agent skill from sd0xdev/sd0x-harness.

    192 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Obsidian CLI

    sd0xdev/sd0x-harness

    Obsidian vault integration via official CLI. An agent skill from sd0xdev/sd0x-harness.

    192 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Orchestrate

    sd0xdev/sd0x-harness

    Agent-driven workflow orchestration (v1 report-only). An agent skill from sd0xdev/sd0x-harness.

    192 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • PR Comment

    sd0xdev/sd0x-harness

    Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review.

    192 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Code Explore

What does Code Explore do?

Pure Claude code investigation. An agent skill from sd0xdev/sd0x-harness. Code Explore is an agent skill from sd0xdev/sd0x-harness. Pure Claude code investigation.

When should I use Code Explore?

Code Explore fits situations like: : tracing execution paths; understanding architecture; diagnosing issues.

How do I install Code Explore in Claude Code?

Run `npx skills add sd0xdev/sd0x-harness --skill code-explore -a claude-code`. Or copy the skill folder (skills/code-explore in sd0xdev/sd0x-harness) into .claude/skills/code-explore in your project. Claude Code loads it when a task matches its description.

How do I install Code Explore in Codex?

Run `npx skills add sd0xdev/sd0x-harness --skill code-explore -a codex`. Or copy the skill folder (skills/code-explore in sd0xdev/sd0x-harness) into .agents/skills/code-explore in your project. Codex loads it when a task matches its description.

Can I use Code Explore 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 sd0xdev/sd0x-harness --skill code-explore -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-explore, .gemini/skills/code-explore, .github/skills/code-explore and .opencode/skills/code-explore in your project.

What does Code Explore need to run?

SKILL.md names no scripts, command-line tools or credentials: Code Explore is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash(ls:*), Bash(find:*).

Does Code Explore 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 Code Explore 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 Code Explore use?

Code Explore 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 Code Explore use?

About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 594 tokens, read only when the agent opens those files.

What are the alternatives to Code Explore?

Skills that share tags, products or a category with Code Explore: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 156k stars) and Understand Diff Analysis (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 Code Explore?

sd0xdev (a GitHub user) maintains it in sd0xdev/sd0x-harness, which has 192 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on October 6, 2026.

Source: sd0xdev/sd0x-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.