Fast — Productivity skill for Claude Code
Execute the current task using FAST mode: inspect, reuse, make the smallest change, verify, simplify.
How to install Fast
Installs to ~/.claude/skills/neuraforge-cl-es-adaptive-engineering-fast/SKILL.md
mkdir -p ~/.claude/skills/neuraforge-cl-es-adaptive-engineering-fast && curl -fsSL https://raw.githubusercontent.com/neuraforge-cl-es/adaptive-engineering/HEAD/commands/fast.md -o ~/.claude/skills/neuraforge-cl-es-adaptive-engineering-fast/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Fast does
name: fast description: "Execute the current task using FAST mode: inspect, reuse, make the smallest change, verify, simplify."
FAST Mode
Use FAST mode for the current task.
- Inspect only the context needed to act safely.
- Reuse existing/native behavior before creating anything.
- Make the smallest coherent change.
- Run targeted verification.
- Simplify the resulting diff.
If a security, data-integrity, public-contract, or production-critical boundary appears, explicitly esc
Alternatives in Productivity
- Worktree Status Check — Verify the current worktree environment and show task details 23.4k ★
- Reviews Plans — Review all active architecture plans relevant to the current task 15.6k ★
- Skill Context Detection — Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type 2.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Modes
When updating your task boundary, you must explicitly set your current agent mode. Think of this as a way of f
Standard
Execute the current task using STANDARD mode with short planning, complexity budget, implementation, tests, si
Gsd Fast
Execute a trivial task inline — no subagents, no planning overhead
Kg Ask
Query the kgai knowledge graph for prior decisions and knowledge relevant to a topic, file, or the current tas
Plan Execute Verify Repair
Run the autonomous-engineering operating loop on a task (plan→implement→verify→repair→report)
Subagent Driven Development
Claude Code skill: execute implementation plans with fresh subagents per task, two-stage review gates, and par
Related Agents
Vc Fast Mode Agent
FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + INNOVATE + PLAN) in one session, then pause for EX
Vela Reviewer
Vela 리뷰어 — v8.0: 리뷰 + 검증(테스트/린트/타입체크) + diff 요약을 단일 에이전트로 통합. mode=review(기본, 5차원 평가), mode=verify(execute 이후
Bolt Executor
Use this agent when there is a clear, well-scoped task to implement in code — a feature, fix, or refactor with