Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

continuous-agent-loop — Claude skill: autonomous agent loops

A skill that lays out a continuous agent loop: mode selection, quality gates, evals and recovery. Useful when an agent runs unattended.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add affaan-m/ECC --skill continuous-agent-loop -a claude-code
Open on GitHub

What continuous-agent-loop does

The skill covers how to run a continuous agent loop. First comes mode selection: strict CI/PR control goes to continuous-pr, RFC decomposition to rfc-dag, parallel generation to infinite, everything else to sequential.

For production it suggests a four-step stack: RFC decomposition via ralphinho-rfc-pipeline, quality gates (plankton-code-quality plus /quality-gate), an eval loop (eval-harness) and session persistence (nanoclaw-repl). It also names the usual failure modes: churn without measurable progress, retries with the same root cause, merge queue stalls, cost drift from unbounded escalation.

When a loop gets stuck, the skill says to freeze it, run /harness-audit, cut scope down to the failing unit and replay with explicit acceptance criteria. Worth installing if you leave agents running in the background and need to see where they broke. For one-off tasks a plain run is enough.

What it helps with

  • pick the right loop mode for a task
  • assemble a production stack of decomposition, gates and evals
  • spot a loop churning without progress
  • break out of repeated retries with one root cause
  • cut scope to the failing unit and replay

Example prompts for the agent

  • Set up a continuous agent loop for this task
  • The loop is churning, freeze it and run /harness-audit
  • Build the stack: ralphinho-rfc-pipeline, quality gates, eval-harness, nanoclaw-repl

How to install continuous-agent-loop

1Skills CLI (Vercel)

npx skills add affaan-m/ECC --skill continuous-agent-loop -a claude-code

2Manually: put the files in place

~/.claude/skills/continuous-agent-loop/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/continuous-agent-loop/

From the same set146

The whole set →
video-editing affaan-m AI-assisted workflow for editing, trimming, and enriching real footage. Connects raw recordings with FFmpeg cuts, Remotion overlays, and ElevenLabs voiceovers. Claude Code CX Codex Cursor +1 6,500installs docker-patterns affaan-m A skill with Dockerfile and Docker Compose patterns: local dev stacks, networking, volumes, container hardening. Claude Code CX Codex Cursor +1 6,300installs frontend-patterns affaan-m A skill for React and Next.js work: component patterns, state, data fetching, and render performance. Use it when building or reviewing UI. Claude Code CX Codex Cursor +1 5,900installs backend-patterns affaan-m A skill with backend patterns for Node.js, Express and Next.js API routes: layering, caching, transactions, error handling. Claude Code CX Codex Cursor +1 5,900installs coding-standards affaan-m Baseline cross-project coding conventions for naming, immutability, and clean code principles. Useful for code reviews and refactoring. Claude Code CX Codex Cursor +1 5,600installs api-design affaan-m Provides REST API design standards covering resource naming, status codes, pagination, and error payloads. Use it when creating or auditing API contracts. Claude Code CX Codex Cursor +1 5,500installs rust-testing affaan-m A skill for writing Rust tests: unit, integration, async, property-based, mocks and coverage. Useful when the project runs on TDD. Claude Code CX Codex Cursor +1 5,500installs laravel-security affaan-m This skill reviews Laravel authentication, Eloquent safety, CSRF, XSS, APIs, and production settings. Use it for security reviews or deployment checks. Claude Code CX Codex Cursor +1 5,400installs

Similar

mmx-cli MiniMax-AI This skill gives an agent access to mmx for MiniMax text, image, video, speech, audio transcription, and web search tasks. Claude Code CX Codex Cursor +1 32,000installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. Claude Code CX Codex Cursor +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. Claude Code Claude.ai 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. Claude Code CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. Claude Code CX Codex Cursor +1 349,200installs

Questions about continuous-agent-loop

How do I install continuous-agent-loop in Claude?

Run npx skills add affaan-m/ECC --skill continuous-agent-loop -a claude-code. The skill file lands at ~/.claude/skills/continuous-agent-loop/SKILL.md.

What does continuous-agent-loop do?

It defines a continuous agent loop: mode selection, quality gates, evals and failure recovery.

How is it different from autonomous-loops?

This is the canonical loop skill name from v1.8+. It supersedes autonomous-loops while keeping compatibility for one release.

Source text

SKILL.md · MIT 
---
name: continuous-agent-loop
description: Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. Use when running an agent loop that must self-check, gate on evals, and recover from failures.
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

© affaan-m · MIT · affaan-m/ECC

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor