continuous-agent-loop

$npx mdskill add affaan-m/ECC/continuous-agent-loop

Manages continuous autonomous agent loops with quality checks and recovery controls

  • Solves problems requiring autonomous execution with quality and cost constraints
  • Uses RFC pipelines, code quality tools, eval harnesses, and session persistence
  • Chooses loop type based on control needs like PR gates, RFCs, or parallel exploration
  • Delivers results through structured execution paths with audit and recovery mechanisms

SKILL.md

.github/skills/continuous-agent-loopView on GitHub ↗
---
name: continuous-agent-loop
description: Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
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

More from affaan-m/ECC

SkillDescription
accessibilityDesign, implement, and audit inclusive digital products using WCAG 2.2 Level AA
agent-architecture-auditFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
agent-evalHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
agent-harness-constructionDesign and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
agent-introspection-debuggingStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
agent-payment-x402Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol.
agent-sortBuild an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
agentic-engineeringOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
agentic-osBuild persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
ai-first-engineeringEngineering operating model for teams where AI agents generate a large share of implementation output.