Skip to main content
Generalhashgraph-online

continuous-agent-loop

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

Stars
336
Source
hashgraph-online/awesome-codex-plugins
Updated
2026-05-27
Slug
hashgraph-online--awesome-codex-plugins--continuous-agent-loop
View on GitHubRaw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/hashgraph-online/awesome-codex-plugins/HEAD/plugins/Colin4k1024/tsp/skills/continuous-agent-loop/SKILL.md -o .claude/skills/continuous-agent-loop.md

Drops the SKILL.md into .claude/skills/continuous-agent-loop.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

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

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