Agent skill

Flow Develop

by nyldn in nyldn/claude-octopus

Multi-AI implementation using available external providers (Double Diamond Develop phase).

MITAuto-check passed

Install Flow Develop

skills CLI
$ npx skills add nyldn/claude-octopus --skill flow-develop -a claude-code

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

GitHub CLI
$ gh skill install nyldn/claude-octopus flow-develop --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/nyldn/claude-octopus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/flow-develop .claude/skills/flow-develop && 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
flow-develop
GitHub stars
4.2k
Used in
1 other repo
Token cost
~7.7k tokens
SKILL.md length
2,382 words
Files
2
Skills in repo
62
Repo updated
First seen
Licence
MIT

At a glance

Multi-AI implementation using available external providers (Double Diamond Develop phase).

  • Works in 12 steps: Detect Work Context (MANDATORY) → Display Visual Indicators (MANDATORY -… → Read Prior State (MANDATORY - State… → …
  • Simple code edits
  • SKILL.md covers Portable feature boundary, Pre-Development: State Check, ⚠️ EXECUTION CONTRACT… and ⚠️ MANDATORY: Context…, plus 5 more sections
  • Calls git, bash and python3; needs OPENAI_API_KEY and AGY_AUTH_TOKEN

What it does

Flow Develop is an agent skill from nyldn/claude-octopus. Multi-AI implementation using available external providers (Double Diamond Develop phase). DO NOT use for simple code edits, reading/reviewing code, built-in commands, or trivial single-file changes.

Its SKILL.md is about 7.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship. The licence is MIT.

When your agent uses it

  • Simple code edits
  • Reading/reviewing code
  • Built-in commands
  • Trivial single-file changes

Example prompts

  • “/flow-develop”

Requirements

  • Python 3
  • Docker

Workflow steps

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

  1. Detect Work Context (MANDATORY)
  2. Display Visual Indicators (MANDATORY - BLOCKING)
  3. Read Prior State (MANDATORY - State Management)
  4. Execute orchestrate.sh develop (MANDATORY - Use Bash Tool)
  5. Verify Execution (MANDATORY - Validation Gate)
  6. Update State (MANDATORY - Post-Execution)
  7. Present Implementation Plan (Only After Steps 1-6 Complete)
  8. Detect Work Context
  9. Output Context-Aware Banner
  10. Invoke Tangle Phase
  11. Multi-Provider Implementation
  12. Review Quality Gates

What it can do on your machine

Read from SKILL.md and the folder at commit 18b66ca. 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:

    • git
    • bash
    • python3
    • jq

    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 these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY
    • AGY_AUTH_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Flow Develop loads about 7.7k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 2,382 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~7.7k

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

The full file from nyldn/claude-octopus at commit 18b66ca, republished under its MIT licence (© nyldn). 2,382 words, ~7,705 tokens.

Download SKILL.mdSave it as .claude/skills/flow-develop/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
flow-develop
description
Multi-AI implementation using available external providers (Double Diamond Develop phase). DO NOT use for simple code edits, reading/reviewing code, built-in commands, or trivial single-file changes.
disable-model-invocation
true

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}}

Load skills/blocks/engineering-method-selection.md from the installed plugin and apply only the methods relevant to this task. Preserve this entry point's execution contract and output format. Read referenced skills as instructions; do not invoke the current command recursively or add provider calls from a seat.

Portable feature boundary

Before implementation, select the existing feature and run its boundary adapter:

bash
OCTO_ROOT="${CLAUDE_PLUGIN_ROOT:-${HOME}/.claude-octopus/plugin}"
bash "$OCTO_ROOT/scripts/helpers/feature-workflow.sh" boundary develop "${OCTOPUS_FEATURE:-}"

Read the bound project policy, relative source and digest. Ask the returned marker batch once through the available native host question tool. Keep skipped or noninteractive decisions open. Report the open count and defer only tasks whose current contract depends on a named unanswered decision. The runtime repeats these checks before actual task dispatch.

Two or more spec/plan/tasks artifacts trigger deterministic analysis automatically. A clean pass uses no extra model seat. Unresolved findings can trigger at most one independent bounded seat, shared across host and runtime for that artifact revision. Unavailable or failed semantic review warns and proceeds. Analysis reports exact source quotations and never rewrites artifacts.

Use stable task IDs and metadata when present. The parent resolves paths, dependencies and current Git state at every wave. A hint cannot grant concurrency or permit overwriting user changes. Legacy inputs retain their existing planner and execution path.

Pre-Development: State Check

Before starting development:

  1. Read .octo/STATE.md to verify Define phase complete
  2. Update STATE.md:
    • current_phase: 3
    • phase_position: "Development"
    • status: "in_progress"
bash
# Verify Define phase is complete
if [[ -f ".octo/STATE.md" ]]; then
  define_status=$("${HOME}/.claude-octopus/plugin/scripts/octo-state.sh" get_phase_status 2)
  if [[ "$define_status" != "complete" ]]; then
    echo "⚠️ Warning: Define phase not marked complete. Consider running definition first."
  fi
fi

# Update state for Development phase
"${HOME}/.claude-octopus/plugin/scripts/octo-state.sh" update_state \
  --phase 3 \
  --position "Development" \
  --status "in_progress"

⚠️ 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:

  • Deliverable terms: "PRD", "proposal", "presentation", "report", "strategy document", "business case"
  • Business terms: "market entry", "competitive analysis", "stakeholder", "executive summary"

Dev Context Indicators:

  • Technical terms: "API", "endpoint", "function", "module", "service", "component"
  • Action terms: "implement", "code", "build", "create", "develop" + technical noun

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

Capture context_type = "Dev" or "Knowledge"

Step 1b: Detect Dev Subtype (if Dev context)

When context_type is Dev, determine the subtype to inject domain-appropriate quality guidance into the prompt sent to providers. Append the matching supplement text after the user's prompt.

SubtypeTrigger keywordsQuality supplement
frontend-ui"page", "widget", "component", "UI", "HTML", "CSS", "form", "dashboard", "layout"See frontend-ui enrichment below.
cli-tool"CLI", "command-line", "terminal", "script", "flag", "argument"Help text via --help flag. Meaningful exit codes (0 success, 1 user error, 2 system error). Stdin/stdout/stderr used correctly. Argument validation with clear error messages.
api-service"API", "endpoint", "REST", "GraphQL", "gRPC", "server", "route"Input validation at boundaries. Consistent error response format. Auth/authz on every endpoint. Rate limiting consideration. OpenAPI/schema documentation.
infra"deploy", "terraform", "docker", "CI", "pipeline", "Kubernetes", "helm"Idempotent operations. Secrets never hardcoded. Rollback path documented. Health checks included.
data"ETL", "pipeline", "migration", "schema", "database", "SQL"Idempotent migrations. Backup/rollback strategy. Data validation at ingestion.
generalDefault if no subtype matchesNo supplement — use base implementer persona only.
frontend-ui enrichment

When frontend-ui subtype is detected, do TWO things:

A. Inject quality supplement into the prompt: Self-contained files preferred. Accessibility: ARIA labels, keyboard nav, 44px touch targets (WCAG 2.5.5). Safe DOM: createElement over innerHTML. Progressive enhancement: feature-detect APIs (navigator.share, localStorage) with fallbacks. Persist user prefs via localStorage.

B. Pull design intelligence from BM25 (if available):

Before calling orchestrate.sh, check if the design intelligence engine exists and query it for relevant design context:

bash
SEARCH_PY="${HOME}/.claude-octopus/plugin/vendors/ui-ux-pro-max-skill/src/ui-ux-pro-max/scripts/search.py"
if [[ -f "$SEARCH_PY" ]]; then
    # Detect relevant domains from the prompt
    design_context=""
    # Style query — what visual style fits this task?
    style_hit=$(python3 "$SEARCH_PY" "<user's task description>" --domain style --top 1 2>/dev/null || true)
    [[ -n "$style_hit" ]] && design_context+="Design style suggestion: $style_hit\n"
    # UX query — relevant UX patterns
    ux_hit=$(python3 "$SEARCH_PY" "<user's task description>" --domain ux --top 1 2>/dev/null || true)
    [[ -n "$ux_hit" ]] && design_context+="UX pattern: $ux_hit\n"
    # Append to prompt if hits found
    if [[ -n "$design_context" ]]; then
        # Append design intelligence to the orchestrate.sh prompt
        prompt="${prompt}\n\nDesign intelligence (from BM25 search):\n${design_context}"
    fi
fi

This gives providers concrete design guidance (style direction, UX patterns) without requiring the user to run /octo:design-ui-ux separately. If the search engine isn't installed, implementation proceeds with the quality supplement only.

How to apply: When calling orchestrate.sh in Step 4, append the quality supplement (and design intelligence if available) to the prompt:

orchestrate.sh develop "<user prompt>\n\nQuality requirements for this deliverable:\n<supplement text>\n<design intelligence if found>"

DO NOT PROCEED TO STEP 2 until context determined. Context type (Dev vs Knowledge) and dev subtype determine which quality supplements and design intelligence to inject — wrong context wastes provider credits on irrelevant analysis.

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 implementation mode
🛠️ [Dev] Develop Phase: [Brief description of what you're building]

Provider Availability:
🔴 Codex CLI: ${codex_status} - Code generation and patterns
🟡 Antigravity CLI: ${agy_status} - Alternative approaches
🧭 Antigravity CLI: ${agy_status} - Additional external-model challenge
🔵 Claude: Available ✓ - Integration and quality gates

💰 Estimated Cost: 0.02-0.10 USD
⏱️  Estimated Time: 3-7 minutes

For Knowledge Context:

🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider implementation mode
🛠️ [Knowledge] Develop Phase: [Brief description of deliverable]

Provider Availability:
🔴 Codex CLI: ${codex_status} - Structure and framework application
🟡 Antigravity CLI: ${agy_status} - Content and narrative development
🧭 Antigravity CLI: ${agy_status} - Additional external-model challenge
🔵 Claude: Available ✓ - Integration and quality review

💰 Estimated Cost: 0.02-0.10 USD
⏱️  Estimated Time: 3-7 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-develop" "develop"

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

# Get context from discover and define phases
discover_context=$("${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" get_context "discover")
define_context=$("${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" get_context "define")

# Display what you found (if any)
if [[ "$discover_context" != "null" ]]; then
  echo "📋 Discovery phase findings:"
  echo "  $discover_context"
fi

if [[ "$define_context" != "null" ]]; then
  echo "📋 Definition phase scope:"
  echo "  $define_context"
fi

if [[ "$prior_decisions" != "[]" && "$prior_decisions" != "null" ]]; then
  echo "📋 Implementing with decisions:"
  echo "$prior_decisions" | jq -r '.[] | "  - \(.decision) (\(.phase)): \(.rationale)"'
fi

This provides critical context for implementation:

  • Technology stack and patterns decided
  • Scope and requirements defined
  • Research findings to inform implementation
  • If claude-mem is installed, its MCP tools (search, timeline, get_observations) are available — use them to check for related past implementation patterns

DO NOT PROCEED TO STEP 4 until state read.

STEP 4: Execute orchestrate.sh develop (MANDATORY - Use Bash Tool)

You MUST execute this command via the native shell command tool:

bash
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh develop "<user's implementation request>"

CRITICAL: You are PROHIBITED from:

  • ❌ Implementing directly without calling orchestrate.sh — single-model implementation misses alternative approaches and edge cases that external providers surface through independent analysis
  • ❌ Writing code without multi-provider perspectives
  • ❌ Claiming you're "simulating" the workflow
  • ❌ Proceeding to Step 4 without running this command

You MUST use the native shell command tool to invoke orchestrate.sh.

What Users See During Execution (v7.16.0+)

If running in Claude Code v2.1.16+, users will see real-time progress indicators in the task spinner:

Phase 1 - External Provider Execution (Parallel):

  • 🔴 Generating code and patterns (Codex)...
  • 🟡 Exploring alternative approaches (Antigravity)...

Phase 2 - Synthesis (Sequential):

  • 🔵 Integrating and applying quality gates...

These spinner verb updates happen automatically - orchestrate.sh calls update_task_progress() before each agent execution. Users see exactly which provider is working and what it's doing.

If NOT running in Claude Code v2.1.16+: Progress indicators are silently skipped, no errors shown.

STEP 5: Verify Execution (MANDATORY - Validation Gate)

After orchestrate.sh completes, verify it succeeded:

bash
# Find the latest synthesis file (created within last 10 minutes)
SYNTHESIS_FILE=$(find ~/.claude-octopus/results -name "tangle-synthesis-*.md" -mmin -10 2>/dev/null | head -n1)

if [[ -z "$SYNTHESIS_FILE" ]]; then
  echo "❌ VALIDATION FAILED: No synthesis file found"
  echo "orchestrate.sh did not execute properly"
  exit 1
fi

echo "✅ VALIDATION PASSED: $SYNTHESIS_FILE"
cat "$SYNTHESIS_FILE"

If validation fails:

  1. Report error to user
  2. Show logs from ~/.claude-octopus/logs/
  3. DO NOT proceed with presenting results
  4. DO NOT substitute with direct implementation — fallback to single-model implementation skips the multi-provider synthesis that catches design flaws early
STEP 6: Update State (MANDATORY - Post-Execution)

After synthesis is verified, record implementation details in state:

bash
# Extract key implementation decisions from synthesis
implementation_approach=$(head -50 "$SYNTHESIS_FILE" | grep -A 3 "## Implementation\|## Approach" | tail -3 | tr '\n' ' ')

# Record implementation decisions
decision_made=$(echo "$implementation_approach" | grep -o "implemented\|using [A-Za-z0-9 ]*\|chose to\|pattern:" | head -1)

if [[ -n "$decision_made" ]]; then
  "${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" write_decision \
    "develop" \
    "$decision_made" \
    "Multi-AI implementation consensus"
fi

# Update develop phase context
"${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" update_context \
  "develop" \
  "$implementation_approach"

# Update metrics
"${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" update_metrics "phases_completed" "1"

DO NOT PROCEED TO STEP 7 until state updated.

STEP 7: Present Implementation Plan (Only After Steps 1-6 Complete)

Read the synthesis file and present:

  • Recommended approach
  • Implementation steps
  • Code overview from all available perspectives
  • Quality gates results
  • Request user confirmation before implementing

After user confirms: Implement the solution using Write/Edit tools

Include attribution:

*Multi-AI Implementation powered by Claude Octopus*
*Providers: available external providers + 🔵 Claude*
*Full implementation plan: $SYNTHESIS_FILE*

Develop Workflow - Develop 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):

  • Deliverable terms: "PRD", "proposal", "presentation", "report", "strategy document", "business case"
  • Business terms: "market entry", "competitive analysis", "stakeholder", "executive summary"

Dev Context Indicators (in prompt):

  • Technical terms: "API", "endpoint", "function", "module", "service", "component"
  • Action terms: "implement", "code", "build", "create", "develop" + technical noun

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

Step 1b: Detect Dev Subtype — see EXECUTION CONTRACT Step 1b above for subtype table and quality supplements. Append the matching supplement to the prompt before calling orchestrate.sh.

Step 2: Output Context-Aware Banner

For Dev Context:

🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider implementation mode
🛠️ [Dev] Develop Phase: [Brief description of what you're building]
📋 Session: ${CLAUDE_SESSION_ID}

Providers:
🔴 Codex CLI - Code generation and patterns
🟡 Antigravity CLI - Alternative approaches
🔵 Claude - Integration and quality gates

For Knowledge Context:

🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider implementation mode
🛠️ [Knowledge] Develop Phase: [Brief description of deliverable]
📋 Session: ${CLAUDE_SESSION_ID}

Providers:
🔴 Codex CLI - Structure and framework application
🟡 Antigravity CLI - Content and narrative development
🔵 Claude - Integration and quality review

{{VISUAL_INDICATORS}}

Part of Double Diamond: DEVELOP (divergent thinking)

       DEVELOP (tangle)

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

       Diverge with
        solutions

What This Workflow Does

The develop phase generates multiple implementation approaches using external CLI providers:

  1. 🔴 Codex CLI - Implementation-focused, code generation, technical patterns
  2. 🟡 Antigravity CLI - Alternative approaches, edge cases, best practices
  3. 🔵 Claude (You) - Integration, refinement, and final implementation

This is the divergent phase for solutions - we explore different implementation paths before converging on the best approach.

When to Use Develop

Use develop when you need:

Dev Context Examples
  • Feature Implementation: "Build a user authentication system"
  • Code Generation: "Create an API endpoint for user registration"
  • Complex Builds: "Implement a caching layer with Redis"
  • Architecture Implementation: "Create a microservice for payment processing"
  • Integration Work: "Integrate Stripe payment processing"
Show full SKILL.md (975 more words)Show less
Knowledge Context Examples
  • PRD Creation: "Build a PRD for the mobile onboarding feature"
  • Strategy Documents: "Create a market entry strategy for APAC"
  • Business Cases: "Build a business case for migrating to cloud"
  • Presentations: "Create an executive presentation on Q2 results"
  • Research Reports: "Build a competitive analysis report"

Don't use develop for:

  • Simple one-line code changes (use Edit tool)
  • Bug fixes (use debugging skills)
  • Code review tasks (use deliver-workflow or review skills)
  • Reading or exploring code (use Read tool)
  • Simple document edits (use Write tool)

Visual Indicators

Before execution, you'll see:

🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider implementation
🛠️ Develop Phase: Building and developing solutions

Providers:
🔴 Codex CLI - Code generation and patterns
🟡 Antigravity CLI - Alternative approaches
🔵 Claude - Integration and refinement

How It Works

Step 1: Invoke Tangle Phase
bash
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh develop "<user's implementation request>"
Step 2: Multi-Provider Implementation

The orchestrate.sh script will:

  1. Call Codex CLI with the implementation task
  2. Call Antigravity CLI with the implementation task
  3. You (Claude) contribute implementation analysis
  4. Synthesize approaches and recommend best path
Step 3: Review Quality Gates

The tangle phase includes automatic quality validation:

  • Code quality checks
  • Security scanning
  • Best practice validation
  • Implementation completeness
Step 3b: Handle Agent Continuation (v9.5 / CC v2.1.77+)

When orchestrate.sh output contains AGENT_TEAMS_RESUME:${agent_id}:${task_id}:${role}:${phase}:

  1. Send a message to the existing agent using SendMessage({to: "${agent_id}", message: "<iteration prompt>"}) — this auto-resumes a stopped agent automatically (CC v2.1.77+)
  2. Read the iteration prompt from the resume instruction JSON at ~/.claude-octopus/agent-teams/${task_id}.json
  3. If SendMessage returns an error (agent GC'd or not found), fall back to creating a new agent with the full prompt from the instruction file
  4. After the agent responds, store its agentId via: bridge_store_agent_id(task_id, agent_id) in the bridge ledger

Note: The Agent(resume: ...) parameter was removed in CC v2.1.77. Always use SendMessage for agent continuation.

Step 4: Read Results

Results are saved to:

~/.claude-octopus/results/${SESSION_ID}/tangle-synthesis-<timestamp>.md
Step 5: Implement Solution

After reviewing all perspectives, implement the final solution using Write/Edit tools.

Implementation Instructions

When this skill is invoked, follow the EXECUTION CONTRACT above exactly. The contract includes:

  1. Blocking Step 1: Detect work context (Dev vs Knowledge)
  2. Blocking Step 2: Check providers, display visual indicators
  3. Blocking Step 3: Execute orchestrate.sh develop via native shell command tool
  4. Blocking Step 4: Verify synthesis file exists
  5. Step 5: Present implementation plan, get user confirmation
  6. After confirmation: Implement the solution using Write/Edit tools

Each step is mandatory and blocking - you cannot proceed to the next step until the current one completes successfully.

Task Management Integration

Create tasks to track execution progress:

javascript
// At start of skill execution
TaskCreate({
  subject: "Execute develop workflow with multi-AI providers",
  description: "Run orchestrate.sh develop for implementation",
  activeForm: "Running multi-AI develop workflow"
})

// Mark in_progress when calling orchestrate.sh
TaskUpdate({taskId: "...", status: "in_progress"})

// Mark completed ONLY after implementation finished
TaskUpdate({taskId: "...", status: "completed"})
Error Handling

If any step fails:

  • Step 1 (Context): Default to Dev Context if ambiguous
  • Step 2 (Providers): If all external providers are unavailable, suggest /octo:setup and STOP
  • Step 3 (orchestrate.sh): Show bash error, check logs, report to user
  • Step 4 (Validation): If synthesis missing, show orchestrate.sh logs, DO NOT substitute with direct implementation

Never fall back to direct implementation if orchestrate.sh execution fails. Report the failure and let the user decide how to proceed.

Implementation Plan Format

After successful execution, present implementation plan with:

# Implementation Plan: <task>

## Recommended Approach
[Your strategic recommendation based on all perspectives]

## Implementation Steps
1. [Step-by-step implementation plan]
2. ...

## Code Overview

### Codex Approach
[Key implementation details from Codex]

### Antigravity Approach
[Alternative considerations from Antigravity]

### Final Implementation
[Your integrated solution]

## Quality Gates
- [ ] Security validation: PASSED/FAILED
- [ ] Best practices: PASSED/FAILED
- [ ] Code quality: PASSED/FAILED

Would you like me to proceed with implementation?
  1. Implement the solution After user confirms, use Write/Edit tools to create the implementation:
    • Create necessary files
    • Write code based on synthesized approach
    • Add tests if applicable
    • Document the implementation

Example Usage

Example 1: Build Authentication System
User: Build a user authentication system with JWT

Claude:
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider implementation mode
🛠️ Develop Phase: Building authentication system

[Executes: ${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh develop "Build a user authentication system with JWT"]

[After completion, reads synthesis and presents:]

# Implementation Plan: User Authentication System

## Recommended Approach

Based on multi-provider analysis, I recommend a layered approach:
1. Auth middleware for JWT validation
2. Login/register endpoints
3. Token refresh mechanism
4. Secure password hashing (bcrypt)

## Implementation Steps

1. Create `src/auth/middleware.ts` - JWT validation middleware
2. Create `src/auth/controller.ts` - Login/register endpoints
3. Create `src/auth/service.ts` - Business logic
4. Create `src/auth/utils.ts` - Token generation/validation
5. Update `src/routes.ts` - Register auth routes

## Code Overview

### Codex Approach
- Modern TypeScript with strict types
- Express middleware pattern
- Redis for token blacklisting
- Comprehensive error handling

### Antigravity Approach
- Passport.js integration suggestion
- Rate limiting on auth endpoints
- Multi-factor auth consideration
- Session management alternatives

### Final Implementation
- Hybrid: Modern TypeScript + Express patterns
- JWT with refresh tokens
- bcrypt password hashing
- Rate limiting included
- Optional MFA hooks for future

## Quality Gates
- ✅ Security validation: PASSED (bcrypt, secure tokens)
- ✅ Best practices: PASSED (TypeScript, error handling)
- ⚠️  Code quality: WARNING (consider adding request validation)

Would you like me to proceed with implementation?

[User: Yes, proceed]

[Claude creates files and implements the solution]
Example 2: Create API Endpoint
User: Create an API endpoint for fetching user notifications

Claude:
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider implementation mode
🛠️ Develop Phase: Creating API endpoint

[Executes tangle workflow]

[Presents implementation plan with multi-provider perspectives]
[Implements the endpoint after user confirmation]

Quality Gates Integration

The tangle phase automatically runs quality checks via .claude/hooks/quality-gate.sh:

bash
# Triggered after tangle execution (PostToolUse hook)
./hooks/quality-gate.sh

{{QUALITY_GATES}}

Integration with Other Workflows

Tangle is the third phase of the Double Diamond:

PROBE (Discover) → GRASP (Define) → TANGLE (Develop) → INK (Deliver)

After tangle completes, you may continue to:

  • Ink: Validate and deliver the implementation

Or use standalone for implementation tasks.

Before Implementation Checklist

Before writing code, ensure:

  • All providers responded with implementation approaches
  • Quality gates evaluated (security, best practices, code quality)
  • User confirmed the implementation plan
  • File structure and architecture are clear
  • Dependencies identified and available
  • Tests planned (if applicable)

After Implementation: Auto Code Review & E2E Verification (MANDATORY)

After implementation completes and before presenting results to the user, you MUST launch two verification agents in parallel. Do NOT skip this step or ask the user whether to run it — it is automatic.

Launch both agents simultaneously:

Agent 1 — Code Review (Sonnet):

Agent(
  model: "sonnet",
  subagent_type: "feature-dev:code-reviewer",
  background execution: true,
  description: "Code review: post-develop",
  prompt: "Review the code changes from this development session. Focus on:
1. Bugs, logic errors, security vulnerabilities
2. Hidden dependencies or coupling issues
3. Whether error handling covers failure modes
4. Adherence to project conventions (check CLAUDE.md)

Check git diff for the changed files. Report only high-confidence issues."
)

Agent 2 — E2E Verification (Sonnet):

Agent(
  model: "sonnet",
  background execution: true,
  description: "E2E test: post-develop",
  prompt: "Run end-to-end verification of the development changes:
1. Run the project's test suite (detect from package.json scripts, Makefile, or pyproject.toml)
2. Verify no regressions in existing tests
3. Check that new files are properly integrated (imported, registered, sourced)
4. Verify the implementation matches the original task requirements

Report: tests passed/failed, any integration issues found."
)

After both agents complete:

  • Present their findings to the user as part of the results
  • If the code reviewer found HIGH-confidence issues, flag them prominently
  • If tests failed, flag before the "what next?" prompt
  • Do NOT block on the review — present findings alongside results

WHY: The user should never have to manually request a code review after development work. Fresh-eyes review from a different model (Sonnet vs Opus) catches issues the implementer is blind to. Running tests automatically catches regressions before the user discovers them.

After Implementation Checklist

After writing code, ensure:

  • All files created/updated
  • Code follows recommended patterns from synthesis
  • Code follows the project's existing commenting conventions (do not add comments unless asked or required by project style)
  • Security concerns addressed
  • Error handling implemented
  • Tests written (if applicable)
  • Lint/typecheck commands run (detect from package.json, pyproject.toml, Cargo.toml, Makefile; if not found, ask the user)
  • If lint/test commands were discovered and not documented in CLAUDE.md, suggest adding them
  • Auto code review completed (Sonnet agent)
  • E2E verification completed (Sonnet agent)
  • User notified of completion with review findings
  • Suggest running ink-workflow for validation

Cost Awareness

External API Usage:

  • 🔴 Codex CLI uses your OPENAI_API_KEY (costs apply)
  • 🟡 Antigravity CLI uses your AGY_AUTH_TOKEN (costs apply)
  • 🔵 Claude analysis included with Claude Code

Tangle workflows typically cost 0.02-0.10 USD per task depending on complexity and code length.

Post-Development: Checkpoint

After development completes:

  1. Run fresh targeted tests for the changed behavior through skill-verification-gate; stop if they fail.
  2. Create checkpoint: git tag octo-checkpoint-post-develop-$(date +%Y%m%d-%H%M%S)
  3. Update .octo/STATE.md with completion and add a history entry with files modified.
bash
# Enter this block only after fresh targeted tests pass.
checkpoint_tag="octo-checkpoint-post-develop-$(date +%Y%m%d-%H%M%S)"
git tag "$checkpoint_tag" -m "Post-develop checkpoint from embrace workflow"
echo "📌 Created checkpoint: $checkpoint_tag"

# Update state only after verification and checkpoint creation succeed.
"${HOME}/.claude-octopus/plugin/scripts/octo-state.sh" update_state \
  --status "complete" \
  --history "Develop phase completed"

# Record files modified in this phase
modified_files=$(git diff --name-only HEAD~1 2>/dev/null || echo "See git log")
"${HOME}/.claude-octopus/plugin/scripts/octo-state.sh" update_state \
  --history "Files modified: $modified_files"

Terminal State

The Develop phase is complete ONLY when the implementation exists, the post-develop checkpoint tag is created, and targeted tests pass fresh (see skill-verification-gate). Then invoke flow-deliver for validation. Do NOT declare the work done from here — completion claims belong to the Deliver phase after review.

Ready to build! This skill is used after explicit invocation when users request implementation or building features.

© nyldn, 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 1 other file in skills/flow-develop of nyldn/claude-octopus.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 18b66ca

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in nyldn/claude-octopus, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Flow Develop 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.

Flow Develop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Flow Develop this skillnyldn/claude-octopus4.2k1 repos~7.7kAutomated safety check: PassMIT
Moodle External API Developmentdavila7/claude-code-templates32k7 repos~4.6kAutomated safety check: PassMIT
DDNS Provider DevelopmentNewFuture/DDNS4.7k—~558Automated safety check: PassMIT
MCP Developmentcoollabsio/coolify63k1 repos~949Automated safety check: PassMIT
Game Developmentsickn33/agentic-awesome-skills47k1 repos~1.3kAutomated safety check: PassMIT
Twenty App Entity Developmenttwentyhq/twenty58k—~1.8kAutomated safety check: PassCustom licence

Similar skills

  • Moodle External API Development

    davila7/claude-code-templates

    Create custom external web service APIs for Moodle LMS. An agent skill from davila7/claude-code-templates.

    32k GitHub starsUsed in 7 repos~4.6k tokens
    DevelopmentAuto-check passed
  • Adds or changes a DNS provider in the DDNS project while keeping its code, schemas, tests and Chinese and English docs consistent.

    4.7k GitHub stars~558 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed
  • Game Development

    sickn33/agentic-awesome-skills

    Game development orchestrator. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~1.3k tokens
    Game DevelopmentAuto-check passed
  • Guides changes to an existing Twenty app: adding or editing objects, layouts, logic functions and front components, with a plan stated before multi-entity edits.

    58k GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Development

    ccusage/ccusage

    Guides ccusage monorepo development. An agent skill from ccusage/ccusage.

    19k GitHub stars~433 tokensUpdated today
    DevelopmentAuto-check passed

More from nyldn/claude-octopus

All 62 skills in this repo
  • Octopus Quick

    nyldn/claude-octopus

    Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests

    4.2k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed
  • Octopus Research

    nyldn/claude-octopus

    Thorough research across multiple sources — use for complex topics needing broad synthesis

    4.2k GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Octopus Security Audit

    nyldn/claude-octopus

    OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews

    4.2k GitHub starsUsed in 1 repo~2.3k tokens
    Auto-check passed
  • Skill Audit

    nyldn/claude-octopus

    Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review

    4.2k GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed
  • Skill Content Pipeline

    nyldn/claude-octopus

    Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages

    4.2k GitHub starsUsed in 1 repo~3.9k tokens
    Auto-check passed
  • Skill Context Detection

    nyldn/claude-octopus

    Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type

    4.2k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check passed

Questions about Flow Develop

What does Flow Develop do?

Multi-AI implementation using available external providers (Double Diamond Develop phase). Flow Develop is an agent skill from nyldn/claude-octopus. Multi-AI implementation using available external providers (Double Diamond Develop phase).

When should I use Flow Develop?

Flow Develop fits situations like: simple code edits; reading/reviewing code; built-in commands; trivial single-file changes.

How do I install Flow Develop in Claude Code?

Run `npx skills add nyldn/claude-octopus --skill flow-develop -a claude-code`. Or copy the skill folder (skills/flow-develop in nyldn/claude-octopus) into .claude/skills/flow-develop in your project. Claude Code loads it when a task matches its description.

How do I install Flow Develop in Codex?

Run `npx skills add nyldn/claude-octopus --skill flow-develop -a codex`. Or copy the skill folder (skills/flow-develop in nyldn/claude-octopus) into .agents/skills/flow-develop in your project. Codex loads it when a task matches its description.

Can I use Flow Develop 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 nyldn/claude-octopus --skill flow-develop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/flow-develop, .gemini/skills/flow-develop, .github/skills/flow-develop and .opencode/skills/flow-develop in your project.

What does Flow Develop need to run?

Going by SKILL.md and its folder, Flow Develop needs the command-line tools its instructions call (git, bash, python3 and jq) and credentials named OPENAI_API_KEY and AGY_AUTH_TOKEN. Our summary lists: Python 3; Docker.

Does Flow Develop access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Flow Develop 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 Flow Develop use?

Flow Develop is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Flow Develop use?

About 7.7k tokens (SKILL.md is roughly 31k 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 Flow Develop?

Skills that share tags, products or a category with Flow Develop: Moodle External API Development (davila7/claude-code-templates, 32k stars), DDNS Provider Development (NewFuture/DDNS, 4.7k stars), MCP Development (coollabsio/coolify, 63k stars) and Game Development (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Flow Develop?

nyldn (a GitHub user) maintains it in nyldn/claude-octopus, which has 4,173 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 7, 2026.

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