Deep Explore

What it does

When your agent uses it

• : large-scale codebase research
• Understanding complex cross-domain systems
• Deep investigation needing multiple perspectives simultaneously

Example prompts

• “/deep-explore”

Requirements

• Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash, Agent

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Parse user's research question
2. 2Estimate scope: Grep for related keywords → count unique files
3. 3Routing guard: if estimated files <= 25, redirect to /code-explore
4. 4Plan shards: identify 2-3 non-overlapping exploration areas

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
  • Agent

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  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

Deep Explore loads about 2.2k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 667 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~99

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.6k

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

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Grep, Glob, Bash, Agent

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). 667 words, ~2,225 tokens.

name

deep-explore

description

Multi-wave parallel code exploration orchestrator. Use when: large-scale codebase research, understanding complex cross-domain systems, deep investigation needing multiple perspectives simultaneously. Not for: quick lookup (use code-explore), dual confirmation (use code-investigate), code review (use codex-code-review). Output: unified exploration report with completeness scoring.

allowed-tools

Read, Grep, Glob, Bash, Agent

flowchart TD
    A[Phase 0: Intent Analysis] --> B{Files > 25?}
    B -->|No| C[Redirect to /code-explore]
    B -->|Yes| D[Wave 1: Breadth]
    D --> E[Gather + Claim Registry]
    E --> F[Wave 2: Depth]
    F --> G{Completeness Gate}
    G -->|score >= 80 + no critical Qs| H[Report]
    G -->|score < 80 OR critical Qs| I[Wave 3: Cross-cutting]
    I --> H

Agent({
  description: "Wave 1 Shard A: <area description>",
  subagent_type: "Explore",
  run_in_background: true,
  prompt: <agent-prompt template from references/agent-prompt.md>
});

score = round(100 × (0.7 × (1 - novelty_rate) + 0.3 × is_zero(critical_open)))

Where:
  novelty_rate = unique_new_findings / max(1, total_valid_findings)
  critical_open = count(questions where impact=high AND uncertainty=high)
  is_zero(x) = 1 if x == 0, else 0

// Primary: Agent tool with subagent_type=Explore
Agent({
  description: "Wave N Shard X: <description>",
  subagent_type: "Explore",
  run_in_background: true,
  prompt: `<from references/agent-prompt.md>`
});

## Deep Exploration Report: <query>

### Completeness
- Score: <N>/100
- Waves executed: <N>
- Agents dispatched: <N>

### Executive Summary
<2-3 sentence answer to user's question>

### Per-Wave Findings
| Wave | Focus | Key Findings | Open Qs |
|------|-------|-------------|---------|

### Claim Registry
| # | Claim | Evidence | Source | Confidence | Consensus |
|---|-------|----------|--------|------------|-----------|

### Coverage Matrix
| Shard | Files Explored | Ownership |
|-------|---------------|-----------|

### Proactive Discoveries (from 20% peripheral)
| # | Finding | Tag | Evidence |
|---|---------|-----|----------|

### Divergence (if any)
| # | Claim A | Claim B | Source Agents | Status |
|---|---------|---------|--------------|--------|

### Residual Risks
- <remaining unknowns and suggested follow-up commands>

Input: /deep-explore "How does the review pipeline work end-to-end?"
Action: Phase 0 → Wave 1 (hooks, skills/review, rules/auto-loop) → Wave 2 (state machine, gate logic) → Report

Input: /deep-explore --areas "hooks, skills/codex-code-review, rules" "Review system architecture"
Action: Phase 0 (user shards) → Wave 1 (3 agents) → Wave 2 (hotspots) → Report

Input: /deep-explore --quick "How does review-state.js work?"
Action: Redirect to /code-explore (small scope)

Input: /deep-explore --agents 2 --waves 2 "Plugin install flow"
Action: Phase 0 → Wave 1 (2 agents) → Wave 2 (2 agents) → Report (max 2 waves)

© 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 2 other files (references) in skills/deep-explore of sd0xdev/sd0x-harness.

• SKILL.md
• references/agent-prompt.md
• references/synthesis.md

Open the folder on GitHubat commit c9a2036