affaan-m/ecc

continuous-agent-loop

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.

All-time #1880 Trending #2573 First seen May 19, 2026
8-week activity · all time api

Installation

$ npx skills add affaan-m/ecc --skill continuous-agent-loop

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from affaan-m/ecc · top by installs.

npx skills add affaan-m/ecc

Browse all from affaan-m/ecc

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 254.3K
License LICENSE
Default branch main
Open issues 54
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

More metadata
origin
ECC

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,190 B
  • docs SUMMARY.md 217 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 8,415 installs

SKILL.md

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