---
name: Flow Discover
slug: flow-discover
category: AI Engineering
description: Flow Discover coordinates multi-AI research across available external providers during the Double Diamond Discover phase. Use it to gather divergent perspectives from multiple AI tools before synthesis.
github: "https://github.com/nyldn/claude-octopus/tree/main/skills/flow-discover"
language: Shell
stars: 3971
forks: 374
install: "npx degit https://github.com/nyldn/claude-octopus/tree/main/skills/flow-discover ~/.claude/skills/flow-discover"
installs_to: ~/.claude/skills/flow-discover
source_path: skills/flow-discover/SKILL.md
collection_size: 25
category_size: 2451
collection_url: "https://dirskills.com/collections/nyldn/claude-octopus"
added: 2026-08-16T07:01:29.853Z
last_synced: 2026-08-16T07:01:29.853Z
canonical_url: "https://dirskills.com/skills/flow-discover"
---

# Flow Discover

Flow Discover coordinates multi-AI research across available external providers during the Double Diamond Discover phase. Use it to gather divergent perspectives from multiple AI tools before synthesis.

**Install:**

```bash
npx degit https://github.com/nyldn/claude-octopus/tree/main/skills/flow-discover ~/.claude/skills/flow-discover
```

## README

> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.
> Cross-reference commands use installed skill names in Codex rather than `/octo:*` slash commands.
> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.
> For host tool equivalents, see `skills/blocks/codex-host-adapter.md`.


{{PREAMBLE}}

## Compaction-Resistant Contract

- Dispatch MUST go through background agents that call `${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh probe-single`; direct single-model research is not a valid substitute.
- Use the dynamic fleet from `build-fleet.sh`; the plugin can route across Codex, Antigravity, Copilot, Qwen, OpenCode, Ollama, Perplexity, OpenRouter, Cursor Agent, and Claude depending on local availability.
- Before synthesis, run `${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh agent-summary` and use only providers reported as `ok`, `degraded`, or `timeout` with usable output.
- For `standard` and `deep` research, require at least 2 usable provider outputs unless fewer providers are installed; failed/rejected providers are reported as gaps, not cited as evidence.

## Pre-Discovery: Optional Project Persistence

Workflow state is stored in the host workspace by default. Only create the
project-local `.octo/` lifecycle artifacts when the user explicitly opts in by
setting `OCTOPUS_PROJECT_PERSISTENCE=true`.

```bash
if [[ "${OCTOPUS_PROJECT_PERSISTENCE:-false}" == "true" ]]; then
  if [[ ! -d ".octo" ]]; then
    echo "📁 Initializing opt-in .octo/ project state..."
    if ! "${HOME}/.claude-octopus/plugin/scripts/octo-state.sh" init_project; then
      echo "Discover incomplete: could not initialize opt-in project state." >&2
      exit 1
    fi
  fi
  if ! "${HOME}/.claude-octopus/plugin/scripts/octo-state.sh" update_state \
      --phase 1 \
      --position "Discovery" \
      --status "in_progress"; then
    echo "Discover incomplete: could not persist in-progress state." >&2
    exit 1
  fi
fi
```


## Native Plan Mode Compatibility (v7.23.0+)

**IMPORTANT:** claude-octopus workflows are designed to persist across context clearing.

### Detecting Native Plan Mode

Check if native plan mode is active:

```bash
# Check for native plan mode markers
if [[ -n "${PLAN_MODE_ACTIVE}" ]] || claude-code plan status 2>/dev/null | grep -q "active"; then
    echo "⚠️  Native plan mode detected"
    echo ""
    echo "   Resolve Claude Octopus workflow state with: octopus state-path"
    echo "   State will persist across plan mode context clears"
    echo "   Multi-AI orchestration will continue normally"
    echo ""
fi
```

### State Persistence Across Context Clearing

**How it works:**
- Native plan mode may clear Claude's memory via `ExitPlanMode`
- Claude Octopus workflow state persists in the host workspace, namespaced by project; resolve its exact path with `state-manager.sh state_path`
- Each workflow phase reads prior state at startup
- Context is automatically restored from files

**No action required** - state management handles this automatically via STEP 3 in the execution contract.


## ⚠️ EXECUTION CONTRACT (MANDATORY - CANNOT SKIP)

This skill uses **ENFORCED execution mode**. You MUST follow this exact sequence.

### STEP 1: Detect Work Context (MANDATORY)

Analyze the user's prompt and project to determine context:

**Knowledge Context Indicators**:
- Business/strategy terms: "market", "ROI", "stakeholders", "strategy", "competitive", "business case"
- Research terms: "literature", "synthesis", "academic", "papers", "personas", "interviews"
- Deliverable terms: "presentation", "report", "PRD", "proposal", "executive summary"

**Dev Context Indicators**:
- Technical terms: "API", "endpoint", "database", "function", "implementation", "library"
- Action terms: "implement", "debug", "refactor", "build", "deploy", "code"

**Also check**: Does project have `package.json`, `Cargo.toml`, etc.? (suggests Dev Context)

**Capture context_type = "Dev" or "Knowledge"**

**DO NOT PROCEED TO STEP 2 until context determined.** Context type (Dev vs Knowledge) determines which provider prompts to use — wrong context produces irrelevant research that wastes provider credits.


### STEP 2: Display Visual Indicators (MANDATORY - BLOCKING)

**MANDATORY: You MUST use the native shell command tool to run this provider check BEFORE displaying the banner. Do NOT skip it. Do NOT assume availability.**

```bash
bash "${HOME}/.claude-octopus/plugin/scripts/helpers/check-providers.sh"
```

**Use the ACTUAL results below. PROHIBITED: Showing only "🔵 Claude: Available ✓" without listing all providers.**

If `OCTO_ALLOWED_PROVIDERS` is set, treat it as the source of truth for which providers may participate. Providers filtered out by that allowlist are intentionally reported as unavailable; do not invoke or recommend them in the workflow.


**Display this banner BEFORE orchestrate.sh execution:**

**For Dev Context:**
```
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode
🔍 [Dev] Discover Phase: [Brief description of technical research]

Provider Availability:
🔴 Codex CLI: ${codex_status}
🟡 Antigravity CLI: ${agy_status}
🧭 Antigravity CLI: ${agy_status}
🟣 Perplexity: ${perplexity_status}
🔵 Claude: Available ✓ (Strategic synthesis)

💰 Estimated Cost: $0.01-0.08
⏱️  Estimated Time: 2-5 minutes
```

**For Knowledge Context:**
```
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode
🔍 [Knowledge] Discover Phase: [Brief description of strategic research]

Provider Availability:
🔴 Codex CLI: ${codex_status}
🟡 Antigravity CLI: ${agy_status}
🧭 Antigravity CLI: ${agy_status}
🟣 Perplexity: ${perplexity_status}
🔵 Claude: Available ✓ (Strategic synthesis)

💰 Estimated Cost: $0.01-0.08
⏱️  Estimated Time: 2-5 minutes
```

**DO NOT PROCEED TO STEP 3 until banner displayed.** The banner shows users which providers will run and what costs they'll incur — starting API calls without this visibility violates cost transparency.


### STEP 3: Read Prior State (MANDATORY - State Management)

**Before executing the workflow, read any prior context:**

```bash
# Initialize state if needed
"${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" init_state

# Set current workflow
"${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" set_current_workflow "flow-discover" "discover"

# Get prior decisions (if any)
prior_decisions=$("${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" get_decisions "all")

# Get context from previous phases
prior_context=$("${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" read_state | jq -r '.context')

# Display what you found (if any)
if [[ "$prior_decisions" != "[]" && "$prior_decisions" != "null" ]]; then
  echo "📋 Building on prior decisions:"
  echo "$prior_decisions" | jq -r '.[] | "  - \(.decision) (\(.phase)): \(.rationale)"'
fi
```

**This provides context from:**
- Prior workflow phases (if resuming a session)
- Architectural decisions already made
- User vision captured in earlier phases
- If **claude-mem** is installed, its MCP tools (`search`, `timeline`, `get_observations`) are available — use them to check for relevant past session context before launching research agents

**DO NOT PROCEED TO STEP 4 until state read.**


### STEP 3.5: Parse Intensity & Build Agent Fleet (MANDATORY)

**Parse the `breadth` and `intensity` parameters from the skill args.** The args string may start with `[breadth=light|standard|exhaustive]` and/or `[intensity=quick|standard|deep]`. If only breadth is specified, map `light -> quick`, `standard -> standard`, and `exhaustive -> deep`. If neither is specified, default to `"standard"` (backward compatible with `/octo:embrace` which doesn't pass intensity).

**Build the fleet dynamically using `build-fleet.sh`** — this is the single source of truth for provider-to-perspective assignment. It detects ALL available providers (codex, agy, copilot, qwen, opencode, ollama, perplexity, openrouter) and assigns perspectives with model family diversity enforcement.

```bash
FLEET_OUTPUT=$("${HOME}/.claude-octopus/plugin/scripts/helpers/build-fleet.sh" research "${INTENSITY}" "${PROMPT}" 2>/dev/null)
```

The output is one line per agent: `agent_type|label|perspective_prompt`

**Parse each line into the fleet array:**
- `agent_type`: the provider to dispatch (codex, agy, copilot, qwen, opencode, claude-sonnet, perplexity, etc.)
- `label`: human-readable name (e.g., "Problem Analysis", "Ecosystem Overview", "Contrarian Analysis")
- `perspective_prompt`: the angle-specific prompt to send to that provider
- `task_id`: generate as `probe-<timestamp>-<index>` for each entry

**Fleet sizes by intensity:**

| Intensity | Agents | Behavior |
|-----------|--------|----------|
| **Quick** | 2 | Two most diverse providers |
| **Standard** | 4-5 | Rotates across available providers + Claude for edge cases and codebase analysis |
| **Deep** | 6-10 | ALL available providers get unique perspectives (bonus slots for copilot, qwen, opencode, etc.) |

**Model family diversity is enforced automatically** — the script prioritizes spreading agents across different model families (OpenAI, Google, Microsoft, Alibaba, Anthropic) to avoid agreement bias from same-family models.

**DO NOT hardcode provider assignments.** Always use build-fleet.sh output. If the script is unavailable, fall back to the available-provider path (for example codex + agy + claude-sonnet when installed).

**DO NOT PROCEED TO STEP 4 until the fleet is built.**


### STEP 4: Launch Parallel Agent Subagents (MANDATORY - Use Agent Tool)

**Launch each perspective as a background Agent subagent.** Each agent calls `orchestrate.sh probe-single` which handles persona application, credential isolation, and result file writing.

**CRITICAL: You MUST use the host subagent tool with `background execution: true` for each perspective.** Launch providers strictly in the runtime FLEET_OUTPUT sequence.

For each perspective in the fleet, launch:

```
Agent(
  background execution: true,
  description: "<label> (<agent_type>)",
  prompt: "Run this command and return its COMPLETE stdout output, including the result file path on the last line:

${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh probe-single <agent_type> '<perspective_prompt>' <task_id> '<original_prompt>'

After the command completes, read the result file path that was printed and return the full file contents."
)
```

**Launch order:** Iterate the parsed `FLEET_OUTPUT` order from `build-fleet.sh`. Launch all entries from that runtime fleet in parallel when possible; do not reorder by hardcoded provider names.

**CRITICAL: You are PROHIBITED from:**
- ❌ Researching directly without calling orchestrate.sh probe-single — single-model research misses perspectives that Codex (implementation depth) and Antigravity (ecosystem breadth) bring
- ❌ Using a single `Bash(orchestrate.sh probe)` call — this causes the 120s Bash timeout that this refactor fixes
- ❌ Using web search instead of orchestrate.sh
- ❌ Claiming you're "simulating" the workflow


### STEP 5: Collect Results (MANDATORY - Wait for Background Agents)

**Wait for all background agents to complete.** You will be automatically notified as each finishes.

**Minimum 2 results required** (same threshold as synthesize_probe_results()). Graceful degradation rules:
- 0 results -> Report error, show logs, DO NOT proceed
- 1 result -> Warn user, proceed with reduced synthesis quality
- 2+ results -> Proceed normally
- If some agents fail/timeout, proceed with successful results

**For each completed agent, collect its output** (the result file contents returned by the agent).

Run the status table before synthesis:

```bash
"${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh" agent-summary
```

Only cite providers with usable output (`ok`, `degraded`, or timeout with partial content). Failed provider output, context-limit errors, and empty outputs are evidence of coverage gaps only.


### STEP 6: Synthesize In-Conversation (MANDATORY - Claude Synthesizes)

**You (Claude) synthesize the collected results directly in conversation.** This replaces the previous direct-provider synthesis call that frequently timed out.

**Use this exact structure** (structured research report format):

1. **Executive Summary** — 2-3 sentence overview answering the original question directly
2. **Key Findings** — Top 3-5 actionable insights, ranked by relevance to the original question
3. **Themes & Patterns** — Where multiple sources agree, grouped by theme
4. **Conflicts & Trade-offs** — Where sources disagree, with your reasoned resolution
5. **Gaps** — What's still unknown and needs more research
6. **Priority Matrix** — Rank findings by impact (High/Medium/Low) and effort (Low/Medium/High) in a table
7. **Recommended Approach** — Specific next steps based on findings
8. **Sources** — List each source with provider attribution and what it contributed
9. **Methodology** — Brief note on providers used, intensity level, and research approach

**Quality rules:**
- Every claim MUST cite its source provider or be explicitly marked as `[inference]`
- Short but specific findings may be MORE valuable than lengthy general analysis
- Minority opinions and dissenting views MUST be preserved — they often contain critical insights
- Concrete examples (code, file paths, commands) outweigh abstract discussion
- Attribute findings to their source provider (🔴 Codex, 🧭 Antigravity, 🔵 Claude Sonnet, 🟣 Perplexity)

**Write synthesis to file:**

```bash
SYNTHESIS_FILE="${HOME}/.claude-octopus/results/probe-synthesis-$(date +%s).md"
mkdir -p "$(dirname "$SYNTHESIS_FILE")"
```

Write the synthesis content to `$SYNTHESIS_FILE`. The file MUST exist for the validation gate.


### STEP 7: Verify, Update State & Present (Only After Steps 1-6 Complete)

**Verify synthesis file exists (probe-synthesis-*.md pattern):**

```bash
# Verify the synthesis file was written (matches probe-synthesis-*.md pattern)
if [[ ! -f "$SYNTHESIS_FILE" ]]; then
  echo "❌ VALIDATION FAILED: No synthesis file found"
  exit 1
fi
echo "✅ VALIDATION PASSED: $SYNTHESIS_FILE"
```

**Update state:**

```bash
key_findings=$(head -50 "$SYNTHESIS_FILE" | grep -A 3 "## Key Findings\|## Summary" | tail -3 | tr '\n' ' ')

"${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" update_context "discover" "$key_findings"
"${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" update_metrics "phases_completed" "1"
# Track actual providers used (dynamic — from fleet output, not hardcoded)
for _provider in $(echo "$FLEET_OUTPUT" | cut -d'|' -f1 | sort -u); do
  "${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" update_metrics "provider" "$_provider"
done
```

**Present results** formatted according to context (Dev vs Knowledge):

**For Dev Context:**
- Technical research summary
- Recommended implementation approach
- Library/tool comparison (if applicable)
- Perspectives from all providers
- Next steps

**For Knowledge Context:**
- Strategic research summary
- Recommended approach with business rationale
- Framework analysis (if applicable)
- Perspectives from all providers
- Next steps

**Include attribution:**
```
*Multi-AI Research powered by Claude Octopus*
*Providers: available external providers + 🔵 Claude*
*Full synthesis: $SYNTHESIS_FILE*
```


# Discover Workflow - Discovery Phase 🔍

## ⚠️ MANDATORY: Context Detection & Visual Indicators

**BEFORE executing ANY workflow actions, you MUST:**

### Step 1: Detect Work Context

Analyze the user's prompt and project to determine context:

**Knowledge Context Indicators** (in prompt):
- Business/strategy terms: "market", "ROI", "stakeholders", "strategy", "competitive", "business case"
- Research terms: "literature", "synthesis", "academic", "papers", "personas", "interviews"
- Deliverable terms: "presentation", "report", "PRD", "proposal", "executive summary"

**Dev Context Indicators** (in prompt):
- Technical terms: "API", "endpoint", "database", "function", "implementation", "library"
- Action terms: "implement", "debug", "refactor", "build", "deploy", "code"

**Also check**: Does the project have `package.json`, `Cargo.toml`, etc.? (suggests Dev Context)

### Step 2: Output Context-Aware Banner with Task Status

**First, check task status (if available):**
```bash
# Get task status summary from orchestrate.sh (v2.1.12+)
task_status=$("${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh" get-task-status 2>/dev/null || echo "")
```

**For Dev Context:**
```
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode
🔍 [Dev] Discover Phase: [Brief description of technical research]
📋 Session: ${CLAUDE_SESSION_ID}
📝 Tasks: ${task_status}

Providers:
🔴 Codex CLI - Technical implementation analysis
🟡 Antigravity CLI - Ecosystem and library comparison
🔵 Claude - Strategic synthesis
```

**For Knowledge Context:**
```
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode
🔍 [Knowledge] Discover Phase: [Brief description of strategic research]
📋 Session: ${CLAUDE_SESSION_ID}

Providers:
🔴 Codex CLI - Data analysis and frameworks
🟡 Antigravity CLI - Market and competitive research
🔵 Claude - Strategic synthesis
```

{{VISUAL_INDICATORS}}


**Part of Double Diamond: DISCOVER** (divergent thinking)

```
    DISCOVER (probe)

    \         /
     \   *   /
      \ * * /
       \   /
        \ /

   Diverge then
    converge
```

## What This Workflow Does

The **discover** phase executes multi-perspective research using external CLI providers:

1. **🔴 Codex CLI** - Technical implementation analysis, code patterns, framework specifics
2. **🟡 Antigravity CLI** - Broad ecosystem research, community insights, alternative approaches
3. **🟣 Perplexity** - Live web search with citations (when PERPLEXITY_API_KEY is set)
4. **🔵 Claude (You)** - Strategic synthesis and recommendation

This is the **divergent** phase - we cast a wide net to explore all possibilities before narrowing down.


## When to Use Discover

Use discover when you need:

### Dev Context Examples
- **Technical Research**: "What are authentication best practices in 2025?"
- **Library Comparison**: "Compare Redis vs Memcached for session storage"
- **Pattern Discovery**: "What are common API pagination patterns?"
- **Ecosystem Analysis**: "What's the state of React server components?"

### Knowledge Context Examples
- **Market Research**: "What are the market opportunities in healthcare AI?"
- **Competitive Analysis**: "Analyze our competitors' pricing strategies"
- **Literature Review**: "Synthesize research on remote work productivity"
- **UX Research**: "What are best practices for user onboarding flows?"

**Don't use discover for:**
- Reading files in the current project (use Read tool)
- Questions about specific implementation details (use code review)
- Quick factual questions Claude knows (no need for multi-provider)


## Visual Indicators

Before execution, you'll see:

```
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider orchestration
🔍 Discover Phase: Research and exploration mode

Providers:
🔴 Codex CLI - Technical analysis
🟡 Antigravity CLI - Ecosystem research
🟣 Perplexity - Live web search (if configured)
🔵 Claude - Strategic synthesis
```


## How It Works

### Step 1: Invoke Discover Phase

```bash
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh discover "<user's research question>"
```

### Step 2: Multi-Provider Research

The orchestrate.sh script will:
1. Call **Codex CLI** with the research question
2. Call **Antigravity CLI** with the research question
3. You (Claude) contribute your analysis
4. Synthesize all perspectives into recommendations

### Step 2a: Native Background Tasks (Claude Code 2.1.14+)

For enhanced coverage, spawn parallel explore agents alongside CLI calls:

```typescript
// Fire parallel background tasks for codebase context
background_task(agent="e