/loop-start
Start a managed autonomous loop pattern with safety defaults.
> /plugin marketplace add loulanyue/awesome-claude-notes > /plugin install awesome-claude-notes@awesome-claude-notes
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/loop-start
Context preview
What this command does when you run it.
Start a managed autonomous loop pattern with safety defaults.
Command definition
loop-start.mddescription: "Start a managed autonomous loop pattern with safety defaults."
Loop Start Command
Start a managed autonomous loop pattern with safety defaults.
Usage
`/loop-start [pattern] [--mode safe|fast]`
- `pattern`: `sequential`, `continuous-pr`, `rfc-dag`, `infinite`
- `--mode`:
- `safe` (default): strict quality gates and checkpoints
- `fast`: reduced gates for speed
Flow
1. Confirm repository state and branch strategy. 2. Select loop pattern and model tier strategy. 3. Enable required hooks/profile for the chosen mode. 4. Create loop plan and write runbook under `.claude/plans/`. 5. Print commands to start and monitor the loop.
Required Safety Checks
- Verify tests pass before first loop iteration.
- Ensure `ECC_HOOK_PROFILE` is not disabled globally.
- Ensure loop has explicit stop condition.
Arguments
$ARGUMENTS:
- `<pattern>` optional (`sequential|continuous-pr|rfc-dag|infinite`)
- `--mode safe|fast` optional
Navigation
- [Command → Agent / Skill Map](../docs/COMMAND-AGENT-MAP.md)
- [Agents index](../AGENTS.md)
- [Contexts directory](../contexts)
- [Contributing guide](../CONTRIBUTING.md)
Community-maintained distribution of reusable AI coding agents, commands, skills, hooks, and cross-harness workflows.
Repo: loulanyue/awesome-claude-notes
Other commands on awesome-claude-notes.
- /aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
Open command - /build-fix
Incrementally fix build and type errors with minimal, safe changes.
Open command - /checkpoint
Create or verify a checkpoint in your workflow.
Open command - /claw
Start NanoClaw v2 — ECC's persistent, zero-dependency REPL with model routing, skill hot-load, branching, compaction, export, and metrics.
Open command - /code-review
Comprehensive security and quality review of uncommitted changes:
Open command - /context-budget
Analyze context window usage across agents, skills, MCP servers, and rules to find optimization opportunities. Helps reduce token overhead and avoid performance warnings.
Open command