Agent skill

Parallel Exploration

by tctinh in tctinh/agent-hive

A skill your agent uses when you need parallel, read-only exploration with the agent tool (Scout fan-out)

Custom licenceAuto-check passed

Install Parallel Exploration

skills CLI
$ npx skills add tctinh/agent-hive --skill parallel-exploration -a claude-code

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

GitHub CLI
$ gh skill install tctinh/agent-hive parallel-exploration --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/tctinh/agent-hive.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/parallel-exploration .claude/skills/parallel-exploration && 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
parallel-exploration
GitHub stars
159
Token cost
~1.8k tokens
SKILL.md length
780 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Custom licence

At a glance

A skill your agent uses when you need parallel, read-only exploration with the agent tool (Scout fan-out)

  • Works in 6 steps: Decompose Into Independent Questions → Invoke Scout Agents in Parallel → Continue Working (Optional) → …
  • You need parallel
  • SKILL.md covers Overview, When to Use, Tool-Aware Research and The Pattern, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Parallel Exploration is an agent skill from tctinh/agent-hive. Use when you need parallel, read-only exploration with the agent tool (Scout fan-out)

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

When your agent uses it

  • You need parallel
  • Read-only exploration with the agent tool (Scout fan-out)

Example prompts

  • “/parallel-exploration”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Decompose Into Independent Questions
  2. Invoke Scout Agents in Parallel
  3. Continue Working (Optional)
  4. Collect Results
  5. Synthesize Findings
  6. Cleanup (If Needed)

What it can do on your machine

Read from SKILL.md and the folder at commit b3f11c0. 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 Exploration loads about 1.8k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 780 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 780 words (~1,796 tokens).

“When you need to answer "where/how does X work?" across multiple domains (codebase, tests, docs, OSS), investigating sequentially wastes time. Each investigation is independent and can happen in parallel.”

— opening of SKILL.md by tctinh, Custom licence
name
parallel-exploration

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .github/skills/parallel-exploration of tctinh/agent-hive.

Open the folder on GitHubat commit b3f11c0

Compare with similar skills

Parallel Exploration 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.

Parallel Exploration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Parallel Exploration this skilltctinh/agent-hive159—~1.8kAutomated safety check: PassCustom licence
Explorersupabase/supabase111k—~845Automated safety check: PassApache-2.0
Parallel Exploringspencerpauly/awesome-cursor-skills842—~787Automated safety check: NotesCC0-1.0
Parallels Discord Roundtripopenclaw/openclaw392k—~788Automated safety check: PassMIT
Openclaw Parallels Smokeopenclaw/openclaw392k—~8.4kAutomated safety check: NotesMIT
Agent Scout Explorerruvnet/ruflo74k3 repos~1.6kAutomated safety check: PassMIT

Similar skills

  • Explorer

    supabase/supabase

    Official

    Build and modify Studio Explorer surfaces, including notebooks, chats, SQL snippets, query cells, and their shared toolbar patterns.

    111k GitHub stars~845 tokensUpdated today
    DatabasesAuto-check passed
  • Parallel Exploring

    spencerpauly/awesome-cursor-skills

    Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously.

    842 GitHub stars~787 tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check: notes
  • Run macOS Parallels smoke with Discord send, host verification, host reply, and guest readback proof.

    392k GitHub stars~788 tokensUpdated today
    Auto-check passed
  • Openclaw Parallels Smoke

    openclaw/openclaw

    Prepare, snapshot, run, rerun, debug, or interpret OpenClaw Parallels guest install, onboarding, gateway smoke, and upgrade checks across macOS, Windows, and Linux.

    392k GitHub stars~8.4k tokensUpdated today
    Auto-check: notes
  • Agent skill for scout-explorer - invoke with $agent-scout-explorer

    74k GitHub starsUsed in 3 repos~1.6k tokens
    Auto-check passed
  • Speed up a task by turning it into a dependency graph of parallel lanes with a lane matrix, batched reads and checks, write surfaces isolated by file, worktree, branch, or service, and a final…

    275k GitHub starsUsed in 1 repo~712 tokens
    DevelopmentAuto-check passed

More from tctinh/agent-hive

  • Agents Md Mastery

    tctinh/agent-hive

    A skill your agent uses when bootstrapping, updating, or reviewing AGENTS.md — teaches what makes effective agent memory, how to structure sections, signal vs noise filtering, and when to prune…

    159 GitHub stars~1.9k tokensUpdated 4 days ago
    Auto-check passed
  • Ast Grep

    tctinh/agent-hive

    Use ast-grep MCP tools for syntax-aware structural search, AST inspection, rule testing, and structural verification.

    159 GitHub stars~1.2k tokensUpdated 4 days ago
    Auto-check passed
  • Docker Mastery

    tctinh/agent-hive

    A skill your agent uses when working with Docker containers — debugging container failures, writing Dockerfiles, docker-compose for integration tests, image optimization, or deploying containerized…

    159 GitHub stars~2.6k tokensUpdated 4 days ago
    Auto-check: notes
  • Verification Reviewer

    tctinh/agent-hive

    A skill your agent uses when independently verifying implementation claims, post-merge review, or when a reviewer needs to falsify success assertions with command-and-output evidence

    159 GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed
  • Code Reviewer

    tctinh/agent-hive

    A skill your agent uses when reviewing implementation changes against an approved plan or task (especially before merging or between Hive tasks) to catch missing requirements, YAGNI, dead code, and…

    159 GitHub stars~1.8k tokensUpdated 4 days ago
    Auto-check passed
  • Parallel Exploration

    tctinh/agent-hive

    A skill your agent uses when you need parallel, read-only exploration with task() (Scout fan-out)

    159 GitHub stars~2k tokensUpdated 4 days ago
    Auto-check passed

Questions about Parallel Exploration

What does Parallel Exploration do?

A skill your agent uses when you need parallel, read-only exploration with the agent tool (Scout fan-out). Parallel Exploration is an agent skill from tctinh/agent-hive.

When should I use Parallel Exploration?

Parallel Exploration fits situations like: you need parallel; read-only exploration with the agent tool (Scout fan-out).

How do I install Parallel Exploration in Claude Code?

Run `npx skills add tctinh/agent-hive --skill parallel-exploration -a claude-code`. Or copy the skill folder (.github/skills/parallel-exploration in tctinh/agent-hive) into .claude/skills/parallel-exploration in your project. Claude Code loads it when a task matches its description.

How do I install Parallel Exploration in Codex?

Run `npx skills add tctinh/agent-hive --skill parallel-exploration -a codex`. Or copy the skill folder (.github/skills/parallel-exploration in tctinh/agent-hive) into .agents/skills/parallel-exploration in your project. Codex loads it when a task matches its description.

Can I use Parallel Exploration 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 tctinh/agent-hive --skill parallel-exploration -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-exploration, .gemini/skills/parallel-exploration, .github/skills/parallel-exploration and .opencode/skills/parallel-exploration in your project.

What does Parallel Exploration need to run?

SKILL.md names no scripts, command-line tools or credentials: Parallel Exploration is instructions for the agent only.

Does Parallel Exploration 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 Exploration 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 Parallel Exploration use?

Parallel Exploration has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Parallel Exploration use?

About 1.8k tokens (SKILL.md is roughly 7.2k 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 Exploration?

Skills that share tags, products or a category with Parallel Exploration: Explorer (supabase/supabase, 111k stars), Parallel Exploring (spencerpauly/awesome-cursor-skills, 842 stars), Parallels Discord Roundtrip (openclaw/openclaw, 392k stars) and Openclaw Parallels Smoke (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Parallel Exploration?

tctinh (a GitHub user) maintains it in tctinh/agent-hive, which has 159 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 4, 2026.

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