Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously.
Install Parallel Exploring
$ npx skills add spencerpauly/awesome-cursor-skills --skill parallel-exploring -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install spencerpauly/awesome-cursor-skills parallel-exploring --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/spencerpauly/awesome-cursor-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/parallel-exploring .claude/skills/parallel-exploring && 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 "parallel-exploring" agent skill from https://github.com/spencerpauly/awesome-cursor-skills/tree/main/resources/parallel-exploring into .claude/skills/parallel-exploring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-exploring", 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/spencerpauly/awesome-cursor-skills/tree/main/resources/parallel-exploringType 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 spencerpauly/awesome-cursor-skills --skill parallel-exploring -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install spencerpauly/awesome-cursor-skills parallel-exploring --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/spencerpauly/awesome-cursor-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/resources/parallel-exploring .agents/skills/parallel-exploring && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "parallel-exploring" agent skill from https://github.com/spencerpauly/awesome-cursor-skills/tree/main/resources/parallel-exploring into .agents/skills/parallel-exploring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-exploring", 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 spencerpauly/awesome-cursor-skills --skill parallel-exploring -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install spencerpauly/awesome-cursor-skills parallel-exploring --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/spencerpauly/awesome-cursor-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/resources/parallel-exploring .cursor/skills/parallel-exploring && 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 "parallel-exploring" agent skill from https://github.com/spencerpauly/awesome-cursor-skills/tree/main/resources/parallel-exploring into .cursor/skills/parallel-exploring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-exploring", 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/spencerpauly/awesome-cursor-skills.git --path resources/parallel-exploring--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 spencerpauly/awesome-cursor-skills --skill parallel-exploring -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install spencerpauly/awesome-cursor-skills parallel-exploring --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/spencerpauly/awesome-cursor-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/resources/parallel-exploring .gemini/skills/parallel-exploring && 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 "parallel-exploring" agent skill from https://github.com/spencerpauly/awesome-cursor-skills/tree/main/resources/parallel-exploring into .gemini/skills/parallel-exploring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-exploring", 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 spencerpauly/awesome-cursor-skills parallel-exploringInstalls 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 spencerpauly/awesome-cursor-skills --skill parallel-exploring -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/spencerpauly/awesome-cursor-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/resources/parallel-exploring .github/skills/parallel-exploring && 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 "parallel-exploring" agent skill from https://github.com/spencerpauly/awesome-cursor-skills/tree/main/resources/parallel-exploring into .github/skills/parallel-exploring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-exploring", 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 spencerpauly/awesome-cursor-skills --skill parallel-exploring -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install spencerpauly/awesome-cursor-skills parallel-exploring --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/spencerpauly/awesome-cursor-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/resources/parallel-exploring .opencode/skills/parallel-exploring && 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 "parallel-exploring" agent skill from https://github.com/spencerpauly/awesome-cursor-skills/tree/main/resources/parallel-exploring into .opencode/skills/parallel-exploring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-exploring", 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
parallel-exploring- GitHub stars
- 841
- Token cost
- ~787 tokens
- SKILL.md length
- 285 words
- Files
- 1
- Skills in repo
- 59
- Repo updated
- First seen
- Licence
- CC0-1.0
At a glance
Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously.
- Works in 3 steps: Identify the areas to explore — break… → Launch parallel explore agents — use the… → Synthesize the results — when all agents…
- Onboarding onto a new project
- SKILL.md covers How It Works, Steps, Other Use Cases and Notes
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Parallel Exploring is an agent skill from spencerpauly/awesome-cursor-skills. Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously. Use when onboarding onto a new project, understanding architecture, or investigating a cross-cutting concern.
Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents. The repository describes itself as: A curated list of awesome skills for Cursor. The licence is CC0-1.0.
When your agent uses it
- Onboarding onto a new project
- Understanding architecture
- Investigating a cross-cutting concern
Example prompts
- “/parallel-exploring”
Requirements
- Docker
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Identify the areas to explore — break the codebase into logical zones. For a typical full-stack app
- Launch parallel explore agents — use the Task tool with subagent_type: "explore" for each area. Launch them all in one message
- Synthesize the results — when all agents return, combine their findings into a coherent picture
What it can do on your machine
Read from SKILL.md and the folder at commit 99cd265. 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.
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
Parallel Exploring loads about 787 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 285 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:34
nt. Check .github/, docker*, *.config.*, .env*.
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 spencerpauly/awesome-cursor-skills at commit 99cd265, republished under its CC0-1.0 licence (© spencerpauly). 285 words, ~787 tokens.
Download SKILL.mdSave it as
.claude/skills/parallel-exploring/SKILL.md (or your agent's skills folder).- name
- parallel-exploring
- description
- Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously. Use when onboarding onto a new project, understanding architecture, or investigating a cross-cutting concern.
Parallel Explore
Use this skill when you need to understand a large or unfamiliar codebase quickly — onboarding onto a new project, investigating how a feature works across layers, or mapping the architecture.
How It Works
Cursor's explore subagent is a fast, read-only agent optimized for searching and reading code. You can launch multiple explore agents in a single message and they run concurrently, each investigating a different area.
Steps
Identify the areas to explore — break the codebase into logical zones. For a typical full-stack app:
- Frontend: components, pages, routing, state management
- Backend: API routes, database models, middleware, auth
- Infrastructure: CI/CD, Docker, deployment config
- Shared: types, utilities, constants
Launch parallel explore agents — use the Task tool with
subagent_type: "explore"for each area. Launch them all in one message:Task 1: "Explore the frontend — find the main pages, routing setup, state management approach, and UI component library. Check src/app/, src/components/, src/pages/. Report the framework, router, styling approach, and key components." Task 2: "Explore the backend — find the API routes, database setup, ORM, auth middleware, and data models. Check src/server/, src/api/, lib/, prisma/. Report the framework, database, auth strategy, and key endpoints." Task 3: "Explore the infrastructure — find CI/CD config, Docker setup, deployment targets, and environment variable management. Check .github/, docker*, *.config.*, .env*. Report the deploy target, CI provider, and any IaC."Synthesize the results — when all agents return, combine their findings into a coherent picture:
- Tech stack summary (frontend, backend, database, infra)
- Architecture diagram (describe the data flow)
- Key files and entry points
- Potential concerns or tech debt
Show full SKILL.md (118 more words)Show less
Other Use Cases
- Cross-cutting investigation: "Where is user authentication checked?" — launch agents to search the frontend (route guards), backend (middleware), and database (session storage) simultaneously.
- Dependency audit: launch agents to check different parts of the dependency tree for outdated packages, security issues, and unused imports.
- Migration planning: have agents simultaneously assess the frontend, backend, and tests to estimate the scope of a framework migration.
Notes
- Explore agents are read-only — they can't modify files.
- Use
thoroughness: "very thorough"in the prompt for comprehensive analysis. - Each agent has its own context window, so they can each read many files without running out of space.
- For a single focused question, just use Grep or SemanticSearch directly — subagents are for broad exploration.
© spencerpauly, CC0-1.0. 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 resources/parallel-exploring of spencerpauly/awesome-cursor-skills.
Open the folder on GitHubat commit 99cd265
Compare with similar skills
Parallel Exploring 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 |
|---|---|---|---|---|---|---|
| Parallel Exploring this skillspencerpauly/awesome-cursor-skills | 841 | — | ~787 | Automated safety check: Notes | CC0-1.0 | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 37k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 40 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
More from spencerpauly/awesome-cursor-skills
All 59 skills in this repoGenerating Images
spencerpauly/awesome-cursor-skills
Generate or edit images using the OpenAI Image API (gpt-image-2).
Babysitting PR
spencerpauly/awesome-cursor-skills
Monitor a pull request for CI failures, review comments, and merge conflicts — then fix them automatically.
Best Of N Solving
spencerpauly/awesome-cursor-skills
Solve a hard problem by trying multiple approaches in parallel using isolated git worktrees.
Grinding Until Pass
spencerpauly/awesome-cursor-skills
Keep iterating on code changes until the tests pass, the build succeeds, or linting is clean.
Parallel CI Triage
spencerpauly/awesome-cursor-skills
When GitHub Actions fails, fetch failing job logs and assign each failing job to a separate subagent that fixes its slice of the problem in parallel.
Profiling Performance
spencerpauly/awesome-cursor-skills
Profile a running web application's CPU performance using Cursor's built-in browser profiler.
Related
Categories
Questions about Parallel Exploring
What does Parallel Exploring do?
Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously. Parallel Exploring is an agent skill from spencerpauly/awesome-cursor-skills. Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously.
When should I use Parallel Exploring?
Parallel Exploring fits situations like: onboarding onto a new project; understanding architecture; investigating a cross-cutting concern.
How do I install Parallel Exploring in Claude Code?
Run `npx skills add spencerpauly/awesome-cursor-skills --skill parallel-exploring -a claude-code`. Or copy the skill folder (resources/parallel-exploring in spencerpauly/awesome-cursor-skills) into .claude/skills/parallel-exploring in your project. Claude Code loads it when a task matches its description.
How do I install Parallel Exploring in Codex?
Run `npx skills add spencerpauly/awesome-cursor-skills --skill parallel-exploring -a codex`. Or copy the skill folder (resources/parallel-exploring in spencerpauly/awesome-cursor-skills) into .agents/skills/parallel-exploring in your project. Codex loads it when a task matches its description.
Can I use Parallel Exploring 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 spencerpauly/awesome-cursor-skills --skill parallel-exploring -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/parallel-exploring, .gemini/skills/parallel-exploring, .github/skills/parallel-exploring and .opencode/skills/parallel-exploring in your project.
What does Parallel Exploring need to run?
SKILL.md names no scripts, command-line tools or credentials: Parallel Exploring is instructions for the agent only. Our summary lists: Docker.
Does Parallel Exploring 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 Parallel Exploring safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Parallel Exploring use?
Parallel Exploring is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Parallel Exploring use?
About 787 tokens (SKILL.md is roughly 3.1k 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 Parallel Exploring?
Skills that share tags, products or a category with Parallel Exploring: Claude Code Agent Development (anthropics/claude-plugins-official, 37k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Parallel Exploring?
spencerpauly (a GitHub user) maintains it in spencerpauly/awesome-cursor-skills, which has 841 GitHub stars. The repository holds 59 skills in this directory. The repository was last updated on August 2, 2026.
Source: spencerpauly/awesome-cursor-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.