octopus-quick
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
What this skill does
> **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`. # Quick Mode - Lightweight Task Execution ⚡ Fast-track execution for small tasks that don't need full Double Diamond workflow overhead. ## When to Use Quick Mode ### ✅ Use Quick Mode For: **Bug Fixes:** - One-file bug fixes with known solution - Typo corrections - Logic error fixes - Import/export corrections **Configuration Changes:** - Update environment variables - Modify config files - Adjust settings - Update dependencies **Small Refactorings:** - Rename variables/functions - Extract helper functions - Simplify logic in single file - Code cleanup **Documentation:** - Fix typos in README - Update comments - Add/update docstrings - Clarify documentation **Dependency Management:** - Update package versions - Add new dependency - Remove unused dependency ### ❌ Don't Use Quick Mode For: **Complex Work:** - New features - Architecture changes - Multi-file refactorings - Security-sensitive changes - Performance optimizations requiring research - Database schema changes - API contract changes **Use full workflows for complex work to ensure quality.** ## Execution Flow Quick mode follows a streamlined process: ``` User Request → Direct Implementation → Atomic Commit → Summary ``` **What Quick Mode SKIPS:** - ❌ Multi-AI research (probe/discover) - ❌ Requirements planning (grasp/define) - ❌ Multi-AI validation (ink/deliver) - ❌ Plan-checker verification **What Quick Mode KEEPS:** - ✅ State tracking (records in state.json) - ✅ Atomic commits (git commit with description) - ✅ Summary generation (stored in .claude-octopus/quick/) - ✅ Change documentation ## Usage ### Via Command ```bash /octo:quick "add dark mode toggle to settings" ``` ### Via Skill Invocation ```bash Use skill: octopus-quick Task: "fix typo in README.md line 42" ``` ### Examples ``` /octo:quick "update Next.js to v15" /octo:quick "fix the broken import in auth.ts" /octo:quick "add error handling to login function" /octo:quick "remove console.log statements" ``` ## Implementation ### Step 1: Understand the Task Quickly assess: - What file(s) need to change? - What's the specific change? - Any dependencies or side effects? ### Step 2: Make the Change Implement directly using appropriate tools: - **Edit** - For modifying existing files - **Write** - For creating new files (rare in quick mode) - **Bash** - For file operations, dependency updates ### Step 3: Create Atomic Commit **Always create a descriptive commit:** ```bash # Stage changes git add [changed-files] # Create commit with clear message git commit -m "quick: [brief description] [Detailed explanation if needed] Co-Authored-By: Claude Sonnet 4.6 <[email protected]>" ``` **Commit message format:** - Prefix with `quick:` to indicate quick mode - Brief description in present tense - Optional detailed explanation - Co-authored tag ### Step 4: Record in State ```bash # Update state with quick task execution "${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" write_decision \ "quick" \ "$(git log -1 --pretty=%s)" \ "Ad-hoc task executed in quick mode" # Update metrics "${HOME}/.claude-octopus/plugin/scripts/state-manager.sh" update_metrics \ "execution_time" \ "1" # Estimated in minutes ``` ### Step 5: Generate Summary ```bash # Create quick task summary mkdir -p .claude-octopus/quick summary_file=".claude-octopus/quick/$(date +%Y%m%d-%H%M%S)-summary.md" cat > "$summary_file" <<EOF # Quick Task: $(git log -1 --pretty=%s) ## Task Description $TASK_DESCRIPTION ## Changes Made $(git diff HEAD~1..HEAD --stat) ## Files Modified $(git diff --name-only HEAD~1..HEAD) ## Commit $(git rev-parse HEAD) ## Timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ) *Executed in Quick Mode - minimal overhead execution* EOF echo "📝 Summary saved to: $summary_file" ``` ## Complete Example **User Request:** ``` /octo:quick "fix typo in README - change 'recieve' to 'receive'" ``` **Execution:** 1. **Read the file** ``` Read README.md to locate the typo ``` 2. **Make the change** ``` Edit README.md: replace "recieve" with "receive" ``` 3. **Commit atomically** ```bash git add README.md git commit -m "quick: fix typo in README (recieve → receive) Co-Authored-By: Claude Sonnet 4.6 <[email protected]>" ``` 4. **Record in state** ```bash state-manager.sh write_decision "quick" \ "Fixed typo in README" \ "Ad-hoc documentation fix" ``` 5. **Generate summary** ```bash Created: .claude-octopus/quick/20260129-143045-summary.md ``` 6. **Report to user** ``` ✅ Fixed typo in README.md 📝 Commit: abc123f 📋 Summary: .claude-octopus/quick/20260129-143045-summary.md ``` ## Benefits of Quick Mode ### Speed ⚡ - No multi-AI orchestration overhead - Direct implementation - Faster for simple tasks ### Cost Savings 💰 - No external provider API calls - Only uses Claude (included with Claude Code) - Efficient for ad-hoc work ### Still Tracked 📊 - Commits recorded - State updated - Summaries generated - Full audit trail maintained ### Appropriate Scope 🎯 - Right tool for small tasks - Doesn't over-engineer simple changes - Reserves full workflows for complex work ## When Quick Mode Isn't Enough If during execution you realize the task is more complex than expected: **Stop and escalate to full workflow:** ``` This task is more complex than anticipated. I recommend using the full workflow instead: - For research: /octo:discover "research authentication patterns" - For planning: /octo:define "define auth requirements" - For building: /octo:develop "implement auth system" - For validation: /octo:deliver "validate auth implementation" Would you like me to switch to a full workflow? ``` **Indicators to escalate:** - Multiple files need changes - Requires architectural decisions - Needs research or comparison - Security implications - Performance implications - Breaking changes ## Directory Structure Quick mode creates summaries in a dedicated directory: ``` .claude-octopus/ └── quick/ ├── 20260129-143045-summary.md ├── 20260129-150122-summary.md └── 20260129-161530-summary.md ``` Each summary includes: - Task description - Changes made - Files modified - Commit hash - Timestamp ## Comparison: Quick Mode vs Full Workflow | Aspect | Quick Mode ⚡ | Full Workflow 🐙 | |--------|-------------|------------------| | **Time** | 1-3 minutes | 5-15 minutes | | **Cost** | Claude only | Codex + Gemini + Claude | | **Providers** | 1 (Claude) | 3 (multi-AI) | | **Research** | None | Comprehensive | | **Planning** | None | Detailed | | **Validation** | Basic | Multi-AI review | | **Best For** | Simple fixes | Complex features | | **When to Use** | Known solution | Unknown solution | ## Best Practices ### DO: - ✅ Use quick mode for straightforward tasks - ✅ Create descriptive commit messages - ✅ Generate summaries for audit trail - ✅ Update state even in quick mode - ✅ Escalate to full workflow if complexity increases ### DON'T: - ❌ Use quick mode for new features - ❌ Skip commits (always commit atomically) - ❌ Skip state updates (maintain consistency) - ❌ Use quick mode for security-sensitive changes - ❌ Force quick mode when full workflow is appropriate ## Troubleshooting ### "Quick mode is taking too long" → Task is probably too complex. Escalate to full workflow. ### "Change broke tests" → Quick mode assumes simple, safe changes. Use full workflow for risky changes. ### "Need to research best approach" → Quick mode is for known solutions only. Use /octo:discover for research. ### "Multiple files need chang
Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".