Explore

Parallel codebase exploration that spawns 3-5 agents to tackle different angles simultaneously: code structure, data flow, architecture patterns, and health assessment. Best for onboarding to unfamiliar repos or understanding how a specific system works under the hood. It asks upfront what you want to explore (full dive, quick scan, just data flow, or patterns), then adapts agent count based on effort level. Outputs include ASCII visualizations, import graphs, and a scored health report. Uses the memory MCP server to remember findings across sessions. The agent coordination is solid but burns tokens on deep exploration, so save it for when you actually need the full picture rather than a quick grep.

skills.sh installs: 224
GitHub stars: 301
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add yonatangross/orchestkit --skill explore --agent claude-code

Installs into .claude/skills of the current project.

Files

Codebase Exploration

Host-neutral workflow. Invoke by skill name (explore). Claude Code slash routing, YAML hook loaders, and .claude/chain live in references/claude-code.md.

Multi-angle codebase exploration using 3-5 parallel agents.

🎯 Quick Start

explore authentication

Opus 5.5: Exploration agents use native adaptive thinking for deeper pattern recognition across large codebases.

STEP -0.5: Effort-Aware Agent Scaling (CC 2.1.120+)

Read $CLAUDE_EFFORT to scale exploration depth before any other decision.

# CC 2.1.120+ env var; explicit --effort= overrides
EFFORT = os.environ.get("CLAUDE_EFFORT")
for token in "$ARGUMENTS".split():
    if token.startswith("--effort="):
        EFFORT = token.split("=", 1)[1]
EFFORT = EFFORT or "high"  # default

Effort	Agent count	Phases	Time
`low`	1 (structure-only)	1, 2, 8	~1 min
`medium`	2 (structure + data flow)	1, 2, 3 (subset), 8	~3 min
`high` (default)	4 (full parallel team)	1–8	~6 min
`xhigh` (Opus 5)	5 (+ uncertainty pass on health scores)	1–8 + caveats	~8 min