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.
Answer "how does X work", "where is X defined", or "trace through Y" questions about a codebase using parallel subagent searches with cited summaries.
Install Explore
$ npx skills add av/mi --skill explore -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install av/mi explore --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/av/mi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/explore .claude/skills/explore && 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 "explore" agent skill from https://github.com/av/mi/tree/master/skills/explore into .claude/skills/explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explore", 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/av/mi/tree/master/skills/exploreType 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 av/mi --skill explore -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install av/mi explore --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/av/mi.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/explore .agents/skills/explore && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "explore" agent skill from https://github.com/av/mi/tree/master/skills/explore into .agents/skills/explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explore", 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 av/mi --skill explore -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install av/mi explore --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/av/mi.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/explore .cursor/skills/explore && 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 "explore" agent skill from https://github.com/av/mi/tree/master/skills/explore into .cursor/skills/explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explore", 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/av/mi.git --path skills/explore--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 av/mi --skill explore -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install av/mi explore --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/av/mi.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/explore .gemini/skills/explore && 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 "explore" agent skill from https://github.com/av/mi/tree/master/skills/explore into .gemini/skills/explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explore", 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 av/mi exploreInstalls 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 av/mi --skill explore -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/av/mi.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/explore .github/skills/explore && 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 "explore" agent skill from https://github.com/av/mi/tree/master/skills/explore into .github/skills/explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explore", 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 av/mi --skill explore -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install av/mi explore --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/av/mi.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/explore .opencode/skills/explore && 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 "explore" agent skill from https://github.com/av/mi/tree/master/skills/explore into .opencode/skills/explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explore", 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
explore- GitHub stars
- 102
- Token cost
- ~958 tokens
- SKILL.md length
- 468 words
- Files
- 1
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- None found
At a glance
Answer "how does X work", "where is X defined", or "trace through Y" questions about a codebase using parallel subagent searches with cited summaries.
- Works in 5 steps: Sharpen the question. Rewrite it as a… → Identify candidate clusters. Breadth… → Spawn one subagent per cluster via node… → …
- Tasks that involve Subagents
- Calls node
What it does
Explore is an agent skill from av/mi. Answer "how does X work", "where is X defined", or "trace through Y" questions about a codebase using parallel subagent searches with cited summaries.
Its SKILL.md is about 960 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: self-extending sandboxed agentic harness. a loop, two tools and an llm.
When your agent uses it
- Tasks that involve Subagents
Example prompts
- “how does X work”
- “where is X defined”
- “trace through Y”
- “/explore”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Sharpen the question. Rewrite it as a single sentence you can hand to each subagent verbatim. If it isn't crisp enough for a grep-guided…
- Identify candidate clusters. Breadth first: ls -la the repo root, read the package manifest (package.json / pyproject.toml / Cargo.toml /…
- Spawn one subagent per cluster via node "$MI_PATH" -p '' with bg=truthy — the harness returns pid:X log:/tmp/mi-X.log and detaches the…
- Summary contract — every subagent writes /tmp/mi-explore-.md with exactly these fields
- While subagents run, maintain a deduped list of FOLLOW_UPS — paths not yet assigned to any cluster — to pursue if clusters come back…
What it can do on your machine
Read from SKILL.md and the folder at commit 2bf50c9. 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
Shell commands in SKILL.md call:
node
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
Explore loads about 958 tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 468 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
Without a licence we can't republish the file, so here is its outline and opening line. It has 468 words (~958 tokens).
“Question-driven, not map-driven. If the user's request is "describe this repo" rather than "where does X happen / how does Y work", push back for a concrete question — a tour without a destination is wasted subagent load.”
- name
- explore
Files
Just SKILL.md in skills/explore of av/mi.
Open the folder on GitHubat commit 2bf50c9
Compare with similar skills
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Explore this skillav/mi | 102 | — | ~958 | Automated safety check: Pass | None | |
| 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 av/mi
All 20 skills in this repoWrites plain-English integration test specs with verifiable steps and expectations, then runs each one through a subagent that reports pass or fail with logs.
Anneal
av/mi
A skill your agent uses when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other…
Scans a codebase to tag every fact as draft, spec or implemented based on what the code actually shows, adding missing facts and fixing or removing wrong ones.
Facts Implementer
av/mi
Implements every @spec fact from a project's fact sheet in code, tags each one @implemented once done, and reports exactly what is left if it cannot finish.
Facts Spec Refiner
av/mi
Works with you to turn draft behavioral facts into precise, implementable spec facts, resolving vague labels, gaps and contradictions one at a time through discussion.
Ideate
av/mi
Timeboxed ideation on a topic using propose-and-critique subagent pairs.
Related
Categories
Questions about Explore
What does Explore do?
Answer "how does X work", "where is X defined", or "trace through Y" questions about a codebase using parallel subagent searches with cited summaries. Explore is an agent skill from av/mi. Answer "how does X work", "where is X defined", or "trace through Y" questions about a codebase using parallel subagent searches with cited summaries.
When should I use Explore?
Explore fits situations like: tasks that involve Subagents.
How do I install Explore in Claude Code?
Run `npx skills add av/mi --skill explore -a claude-code`. Or copy the skill folder (skills/explore in av/mi) into .claude/skills/explore in your project. Claude Code loads it when a task matches its description.
How do I install Explore in Codex?
Run `npx skills add av/mi --skill explore -a codex`. Or copy the skill folder (skills/explore in av/mi) into .agents/skills/explore in your project. Codex loads it when a task matches its description.
Can I use 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 av/mi --skill 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/explore, .gemini/skills/explore, .github/skills/explore and .opencode/skills/explore in your project.
What does Explore need to run?
Going by SKILL.md and its folder, Explore needs the command-line tools its instructions call (node).
Does 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 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 Explore use?
No licence was found for Explore or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Explore use?
About 958 tokens (SKILL.md is roughly 3.8k 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 Explore?
Skills that share tags, products or a category with Explore: 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 Explore?
av (a GitHub user) maintains it in av/mi, which has 102 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on September 26, 2026.
Source: av/mi on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.