mirror of
https://github.com/affaan-m/everything-claude-code.git
synced 2026-04-07 17:53:32 +08:00
feat: deliver v1.8.0 harness reliability and parity updates
This commit is contained in:
45
skills/continuous-agent-loop/SKILL.md
Normal file
45
skills/continuous-agent-loop/SKILL.md
Normal file
@@ -0,0 +1,45 @@
|
||||
---
|
||||
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
|
||||
Reference in New Issue
Block a user