Skillshub continuous-agent-loop

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

install

source · Clone the upstream repo

git clone https://github.com/ComeOnOliver/skillshub

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/ComeOnOliver/skillshub "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/affaan-m/everything-claude-code/continuous-agent-loop" ~/.claude/skills/comeonoliver-skillshub-continuous-agent-loop && rm -rf "$T"

manifest: skills/affaan-m/everything-claude-code/continuous-agent-loop/SKILL.md

source content

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:

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