Imported from mdnaimul22/human-skills (skills/storage/affaan-m_ECC/continuous-agent-loop/SKILL.md). Install upstream with npx skills add mdnaimul22/human-skills --skill continuous-agent-loop. Copyright stays with the author.

Continuous Agent Loop

Name: continuous-agent-loop
Author: mdnaimul22

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

Loop Selection Flow

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:

RFC decomposition (ralphinho-rfc-pipeline)
quality gates (plankton-code-quality + /quality-gate)
eval loop (eval-harness)
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

{ "ocm": "1", "id": "mdnaimul22-human-skills-continuous-agent-loop", "kind": "skill", "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.", "publisher": "mdnaimul22", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "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." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/mdnaimul22/human-skills", "path": "skills/storage/affaan-m_ECC/continuous-agent-loop/SKILL.md", "ref": "fbc4c822b016c12e9fed5428e1660c74583772fc", "url": "https://github.com/mdnaimul22/human-skills/blob/fbc4c822b016c12e9fed5428e1660c74583772fc/skills/storage/affaan-m_ECC/continuous-agent-loop/SKILL.md", "key": "mdnaimul22/human-skills/skills/storage/affaan-m_ECC/continuous-agent-loop/SKILL.md" } }, "instructions": "# Continuous Agent Loop\n\nThis is the v1.8+ canonical loop skill name. It supersedes `autonomous-loops` while keeping compatibility for one release.\n\n## Loop Selection Flow\n\n```text\nStart\n |\n +-- Need strict CI/PR control? -- yes --> continuous-pr\n |\n +-- Need RFC decomposition? -- yes --> rfc-dag\n |\n +-- Need exploratory parallel generation? -- yes --> infinite\n |\n +-- default --> sequential\n```\n\n## Combined Pattern\n\nRecommended production stack:\n1. RFC decomposition (`ralphinho-rfc-pipeline`)\n2. quality gates (`plankton-code-quality` + `/quality-gate`)\n3. eval loop (`eval-harness`)\n4.", "cost": { "context_tokens": 230 } }

continuous-agent-loop

About

Continuous Agent Loop

Loop Selection Flow

Combined Pattern

Failure Modes

Recovery

Use it

Manifest

Reviews