continuous-agent-loop
Runs a self-checking robot loop that fixes its own mistakes and keeps working safely.
Installation
Paste this into Claude Code, Cursor, or any agent that can run commands.
What this skill does
What it does:
- Runs a repeating cycle where an AI agent works on a task, checks the quality, and fixes problems
- Includes safety checks to stop the agent from making the same mistake over and over
- Breaks down big requests into smaller pieces to solve them one at a time
- Saves progress so work does not get lost
When to use it:
- You want an AI to keep working on code or a project until it is done right
- You need the AI to check its own work and fix errors automatically
- You have a big task that needs to be split into smaller steps
- You want to make sure the AI does not waste time repeating the same failed attempts
SKILL.mdShow the author's original SKILL.md
--- name: continuous-agent-loop description: Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. metadata: origin: ECC --- # Continuous Agent Loop This is the v1.8+ canonical loop skill name. It supersedes `autonomous-loops` while keeping compatibility for one release. ## Loop Selection Flow ```text Start | +-- Need strict CI/PR control? -- yes --> continuous-pr | +-- Need RFC decomposition? -- yes --> rfc-dag | +-- Need exploratory parallel generation? -- yes --> infinite | +-- default --> sequential ``` ## Combined Pattern Recommended production stack: 1. RFC decomposition (`ralphinho-rfc-pipeline`) 2. quality gates (`plankton-code-quality` + `/quality-gate`) 3. eval loop (`eval-harness`) 4. session persistence (`nanoclaw-repl`) ## Failure Modes - loop churn without measurable progress - repeated retries with same root cause - merge queue stalls - cost drift from unbounded escalation ## Recovery - freeze loop - run `/harness-audit` - reduce scope to failing unit - replay with explicit acceptance criteria
Mirrored from the author's public source. Install counts from the open skills registry.