All skills
richtabor avatar

/ralph-json-start-loop

@e0eb0bb
by Rich Taborrichtabor/agent-skills72 stars
10

Runs the Ralph autonomous loop. Executes stories from prds/*.json using git worktrees.

Use this Skill: https://skilld.dev/gh/richtabor/agent-skills/ralph-json-start-loop

This session only. Nothing lands on disk.

SKILL.md

≈27 tokens always: the name and description. ≈375 when used: this file. ≈936 more on demand in 1 file.

Ralph

Run the autonomous loop to execute features from prds/ directory.

Usage

/ralph              # Run next available project (respects dependencies)
/ralph 25           # Run with 25 iterations
/ralph auth-flow    # Run specific project

Process

Run the loop script in background mode:

~/.claude/skills/ralph/ralph.sh [iterations] [project-name]

Use run_in_background: true to prevent timeout. After starting, tell the user to check progress with tail -f <worktree>/.ralph-progress.txt.

What It Does

  1. Shows dependency graph, finds next available project
  2. Creates git worktree at ../{repo}-{feature}/
  3. For each iteration:
    • Picks first story where passes: false
    • Implements it, runs quality checks
    • Commits: feat: [id] - [title]
    • Updates JSON, syncs back to main repo
  4. When all stories pass, outputs <promise>COMPLETE</promise>

Dependencies

Ralph reads dependsOn from each PRD and enforces ordering:

{
  "projectName": "Dashboard",
  "dependsOn": ["auth-flow", "user-profile"]
}

Projects with incomplete dependencies are blocked. Ralph picks the first ready project alphabetically.

Prerequisites

  1. At least one .json PRD file in .claude/plans/, plans/, or prds/
  2. Use plan mode to create a plan, then run /ralph-json-create-issues to convert it

Notes

  • Run multiple Ralphs in parallel on independent projects (separate terminals)
  • Each works in its own worktree, no conflicts

Source: SKILL.md on GitHub

1 alert9d4 checks · Risk HIGH
  • Gen Agent Trust Hub9d

    This skill implements an autonomous coding loop that bypasses standard security permissions and is vulnerable to indirect prompt injection through project requirement files.

  • Socket9d

    1 alert: gptSecurity

  • Snyk9d

    Risk: LOW · No issues

  • Runlayer7mo

    3/3 files flagged

Signed by skilld at e0eb0bb. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Steadyupdated 8 months ago
disable-model-invocation
true
argument-hint
[iterations] [project-name]

README badge

README badge for richtabor/agent-skills/ralph-json-start-loop