ralph-router
- Repo stars 1
- Author repo Ralph-Anti-loop-Bundle-Skill
Ralph Router — Automatic level selection
Before you act, pick the right level. Never start a task without loading the correct skill.
Decision tree
I receive a task.
│
├─ How many steps do I expect?
│ │
│ ├─ 1–3 steps / single operation / lookup / quick edit
│ │ └─ → Load ralph-small
│ │ Path: /home/ubuntu/.openclaw/skills/ralph-small/SKILL.md
│ │
│ ├─ 4–10 steps / sequential workflow / moderate dependencies
│ │ └─ → Load ralph-medium
│ │ Path: /home/ubuntu/.openclaw/skills/ralph-medium/SKILL.md
│ │
│ └─ 10+ steps / debugging / refactor / architecture / high complexity
│ └─ → Load ralph-huge
│ Path: /home/ubuntu/.openclaw/skills/ralph-huge/SKILL.md
│
├─ Unsure about complexity?
│ └─ → Err on the side of more discipline. Prefer ralph-medium on a simple task
│ over ralph-small on a task that turns out complex.
│
└─ Already using ralph-small or ralph-medium and exhausted attempts?
└─ → Escalate to the next level immediately.
Do not wait. Do not retry the same tier. Escalate.
Automatic escalation rule
ralph-small → 2 failed attempts → ralph-medium
ralph-medium → 3 failed attempts → ralph-huge
ralph-huge → 4 failed attempts → Circuit breaker + wait for user
There is no escalation beyond ralph-huge. After four failed unique attempts, stop, emit the diagnostic, and wait for human input.
After success (self-improvement)
When the task was run under ralph-small, ralph-medium, or ralph-huge and you have verified success (evidence in the same turn):
- Follow the Closure: self-improvement section at the end of whichever Ralph level you used — it links to
self-improvementand.learnings/without blocking the user reply. - Skill path (OpenClaw):
/home/ubuntu/.openclaw/skills/self-improvement/SKILL.md
This is optional but high-value for recurring patterns, non-obvious fixes, and tool/gateway gotchas.
Note for the agent
Never tell the user “I’m using ralph-[level]” — that is internal operations detail. Select, load, act. The user wants outcomes, not narration of your selection process.
- Fluxly category
- Other
- Author-declared agents
- No explicit declaration found; this is not inferred or tested compatibility
- Static check
- 92 / 100 · heuristic scan, not runtime safety proof
- Author / version / license
- @00Blacksheep00 · v1.0 · no license declared
- Fluxly token estimate
- Lean
- Fluxly setup estimate
- Plug-and-play
- External API key
- No requirement detected
- Detected OS requirements
- Linux
- Runtime requirements
- Unspecified
- Detected file/system behavior
-
- Read-only
- Write / modify
- Detected network behavior
- Local-only
- Install commands
- None (reference only)
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
The current SKILL.md does not define a fixed output example. Decision tree
There is no escalation beyond ralph-huge. After four failed unique attempts, stop, emit the diagnostic, and wait for human input.
When the task was run under ralph-small, ralph-medium, or ralph-huge and you have verified success (evidence in the same turn): Follow the Closure: self-improvement section at the end of whichever Ralph level you used — it links to self-improvement and…
Never tell the user “I’m using ralph-[level]” — that is internal operations detail. Select, load, act. The user wants outcomes, not narration of your selection process.
# Ralph Router — Automatic level selection
> Before you act, pick the right level. Never start a task without loading the correct skill.
---
## Decision tree
```
I receive a task.
│
├─ How many steps do I expect?
│ │
│ ├─ 1–3 steps / single operation / lookup / quick edit
│ │ └─ → Load ralph-small
│ │ Path: /home/ubuntu/.openclaw/skills/ralph-small/SKILL.md
│ │
│ ├─ 4–10 steps / sequential workflow / moderate dependencies
│ │ └─ → Load ralph-medium
│ │ Path: /home/ubuntu/.openclaw/skills/ralph-medium/SKILL.md
│ │
│ └─ 10+ steps / debugging / refactor / architecture / high complexity
│ └─ → Load ralph-huge
│ Path: /home/ubuntu/.openclaw/skills/ralph-huge/SKILL.md
│
├─ Unsure about complexity?
│ └─ → Err on the side of more discipline. Prefer ralph-medium on a simple task
│ over ralph-small on a task that turns out complex.
│
└─ Already using ralph-small or ralph-medium and exhausted attempts?
└─ → Escalate to the next level immediately.
Do not wait. Do not retry the same tier. Escalate.
```
---
## Automatic escalation rule
```
ralph-small → 2 failed attempts → ralph-medium
ralph-medium → 3 failed attempts → ralph-huge
ralph-huge → 4 failed attempts → Circuit breaker + wait for user
```
**There is no escalation beyond ralph-huge.** After four failed unique attempts, stop, emit the diagnostic, and wait for human input.
---
## After success (self-improvement)
When the task was run under **ralph-small**, **ralph-medium**, or **ralph-huge** and you have **verified** success (evidence in the same turn):
… Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.
sections -> Decision tree → Automatic escalation rule → After success (self-improvement) → Note for the agent
terms -> There is no escalation beyond ralph-huge. · ralph-small · ralph-medium · ralph-huge · verified · Closure: self-improvement · self-improvement
files/cmd -> self-improvement · .learnings/ · /home/ubuntu/.openclaw/skills/self-improvement/SKILL.md · home/ubuntu/.openclaw/skills/ralph-small/SKILL.md · home/ubuntu/.openclaw/skills/ralph-medium/SKILL.md · home/ubuntu/.openclaw/skills/ralph-huge/SKILL.md · home/ubuntu/.openclaw/skills/self-improvement/SKILL.md · tool/gateway
body sha256 -> 73c9fa90244e
Decide Fit First
Design Intent
How To Use It
Boundaries And Review