ReddRadar
Agent skill
ralph-loop
Execute an autonomous development loop that picks one task per iteration, implements it, verifies it, and commits the result — each iteration in a fresh context window. Use when user runs /ralph, mentions "ralph loop", "autonomous loop", "builder verifier", "run tasks automatically", "iterate on tasks", "develop autonomously", or wants an automated build-verify-commit cycle with task tracking.
Install this agent skill to your Project
npx add-skill https://github.com/joaquimscosta/arkhe-claude-plugins/tree/main/plugins/ralph/skills/ralph-loop
SKILL.md
Ralph Loop Execution Protocol
Autonomous development with fresh context per iteration and Hat-lite builder/verifier workflow.
Quick Start
# From project directory (after /create-prd)
./ralph.sh 20 # Run up to 20 iterations
./ralph.sh 5 # Quick test with 5 iterations
How It Works
Each iteration runs in a fresh context window:
┌─────────────────────────────────────────────────────┐
│ ITERATION (Fresh Context) │
├─────────────────────────────────────────────────────┤
│ 1. ORIENT: Read activity.log + tasks.json + memories│
│ 2. BUILD: Pick ONE task, implement, verify │
│ 3. VERIFY: Review, update status, commit │
│ 4. LEARN: (Optional) Save insights to memories │
│ 5. DECIDE: All done? → RALPH_COMPLETE │
└─────────────────────────────────────────────────────┘
Hat-Lite System
| Role | When | Responsibility |
|---|---|---|
| Builder | ~65% of iteration | Implement ONE task |
| Verifier | ~35% of iteration | Review, update, commit |
Key Files
| File | Purpose |
|---|---|
.ralph/current-taskset/tasks.json |
Task state (source of truth) |
.ralph/current-taskset/activity.log |
Iteration history |
.ralph/current-taskset/memories.md |
Persistent learnings |
.ralph/current-taskset |
Symlink to active task set |
PROMPT.md |
Instructions per iteration |
ralph.sh |
Loop runner script |
Task JSON Format
Tasks are stored in .ralph/current-taskset/tasks.json:
{
"tasks": [
{
"id": "setup-001",
"description": "Initialize project",
"verificationTier": "build",
"passes": false,
"iteration_completed": null
}
]
}
Valid verificationTier values: "build" (default), "visual", "api", "e2e". See WORKFLOW.md for details.
Completion Signal
When all tasks pass, output:
RALPH_COMPLETE: All tasks verified
Commands
Subcommands: /ralph run [N], /ralph status, /ralph init, /ralph taskset <new|list|switch|delete>, /ralph add-task, /ralph remember, /ralph memories.
Workflow Details
See WORKFLOW.md for the 5-phase iteration lifecycle (Orient, Build, Verify, Learn, Decide) and Hat-Lite role definitions.
Examples
See EXAMPLES.md for web app, API, resumption, and mid-loop status checking scenarios.
Troubleshooting
See TROUBLESHOOTING.md for immediate exit, premature completion, infinite loop, and context issues.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
joaquimscosta/arkhe-claude-plugins
Skill Name
What this skill does. Use when user mentions "keyword1", "keyword2", or "keyword3". Keep under 1,024 characters and include specific trigger keywords.
joaquimscosta/arkhe-claude-plugins
plugin-release-checker
joaquimscosta/arkhe-claude-plugins
skill-validator
Validate skills against Anthropic best practices for frontmatter, structure, content, file organization, hooks, MCP, and security (62 rules in 8 categories). Use when creating new skills, updating existing skills, before publishing skills, reviewing skill quality, or when user mentions "validate skill", "check skill", "skill best practices", "skill review", or "lint skill".
joaquimscosta/arkhe-claude-plugins
sync-docs
Sync official Anthropic documentation and analyze impact on project components. Runs docs/reference/update-claude-docs.sh, computes diffs, and reports impacts on the skill validator, plugins, and project documentation. Use when user mentions "sync docs", "update reference docs", "refresh docs", or "check doc changes".
joaquimscosta/arkhe-claude-plugins
research-frontmatter
Enforce standard YAML frontmatter on research documents in docs/research/. Use when creating, editing, or promoting research files, when user mentions "research metadata", "research frontmatter", or "research staleness".
joaquimscosta/arkhe-claude-plugins
deep-research
Deep research on technical topics using EXA tools with intelligent two-tier caching. Use when user asks to research a topic, investigate best practices, look up information, find patterns, or explore architectures. Also invoked by /research command. Triggers: "research", "look up", "investigate", "deep dive", "find information about", "what are best practices for", "how do others implement".
Didn't find tool you were looking for?