Agent skill
flow-next-ralph-init
Scaffold repo-local Ralph autonomous harness under scripts/ralph/. Use when user runs /flow-next:ralph-init.
Install this agent skill to your Project
npx add-skill https://github.com/gmickel/flow-next/tree/main/plugins/flow-next/skills/flow-next-ralph-init
SKILL.md
Ralph init
Scaffold or update repo-local Ralph harness. Opt-in only.
Rules
- Only create/update
scripts/ralph/in the current repo. - If
scripts/ralph/already exists, offer to update (preserves config.env). - Copy templates from
templates/intoscripts/ralph/. - Copy
flowctlandflowctl.pyfrom${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/intoscripts/ralph/. - Set executable bit on
scripts/ralph/ralph.sh,scripts/ralph/ralph_once.sh, andscripts/ralph/flowctl.
Workflow
-
Resolve repo root:
git rev-parse --show-toplevel -
Check if
scripts/ralph/exists:- If exists: ask "Update existing Ralph setup? (preserves config.env and runs/) [y/n]"
- If no: stop
- If yes: set UPDATE_MODE=1
- If not exists: set UPDATE_MODE=0
- If exists: ask "Update existing Ralph setup? (preserves config.env and runs/) [y/n]"
-
Detect available review backends (skip if UPDATE_MODE=1):
bashHAVE_RP=$(which rp-cli >/dev/null 2>&1 && echo 1 || echo 0) HAVE_CODEX=$(which codex >/dev/null 2>&1 && echo 1 || echo 0) -
Determine review backend (skip if UPDATE_MODE=1):
- If BOTH available, ask user (do NOT use AskUserQuestion tool):
Wait for response. Default if empty/ambiguous:
Both RepoPrompt and Codex available. Which review backend? a) RepoPrompt (macOS, visual builder) b) Codex CLI (cross-platform, GPT 5.2 High) (Reply: "a", "rp", "b", "codex", or just tell me)rp - If only rp-cli available: use
rp - If only codex available: use
codex - If neither available: use
none
- If BOTH available, ask user (do NOT use AskUserQuestion tool):
-
Copy files using bash (MUST use cp, NOT Write tool):
If UPDATE_MODE=1 (updating):
bash# Backup config.env cp scripts/ralph/config.env /tmp/ralph-config-backup.env # Update templates (preserves runs/) cp "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/skills/flow-next-ralph-init/templates/ralph.sh" scripts/ralph/ cp "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/skills/flow-next-ralph-init/templates/ralph_once.sh" scripts/ralph/ cp "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/skills/flow-next-ralph-init/templates/prompt_plan.md" scripts/ralph/ cp "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/skills/flow-next-ralph-init/templates/prompt_work.md" scripts/ralph/ cp "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/skills/flow-next-ralph-init/templates/prompt_completion.md" scripts/ralph/ cp "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/skills/flow-next-ralph-init/templates/watch-filter.py" scripts/ralph/ cp "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/flowctl" "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/flowctl.py" scripts/ralph/ mkdir -p scripts/ralph/hooks cp "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/hooks/ralph-guard.py" scripts/ralph/hooks/ chmod +x scripts/ralph/ralph.sh scripts/ralph/ralph_once.sh scripts/ralph/flowctl scripts/ralph/hooks/ralph-guard.py # Restore config.env cp /tmp/ralph-config-backup.env scripts/ralph/config.envIf UPDATE_MODE=0 (fresh install):
bashmkdir -p scripts/ralph/runs scripts/ralph/hooks cp -R "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/skills/flow-next-ralph-init/templates/." scripts/ralph/ cp "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/flowctl" "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/flowctl.py" scripts/ralph/ cp "${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/hooks/ralph-guard.py" scripts/ralph/hooks/ chmod +x scripts/ralph/ralph.sh scripts/ralph/ralph_once.sh scripts/ralph/flowctl scripts/ralph/hooks/ralph-guard.pyNote:
cp -R templates/.copies all files including dotfiles (.gitignore). -
Edit
scripts/ralph/config.envto set the chosen review backend (skip if UPDATE_MODE=1):- Replace
PLAN_REVIEW={{PLAN_REVIEW}}withPLAN_REVIEW=<chosen> - Replace
WORK_REVIEW={{WORK_REVIEW}}withWORK_REVIEW=<chosen> - Replace
COMPLETION_REVIEW={{COMPLETION_REVIEW}}withCOMPLETION_REVIEW=<chosen>
- Replace
-
Print next steps (run from terminal, NOT inside Claude Code):
If UPDATE_MODE=1:
Ralph updated! Your config.env was preserved. Changes in this version: - Removed local hooks requirement (plugin hooks work when installed normally) Run from terminal: - ./scripts/ralph/ralph_once.sh (one iteration, observe) - ./scripts/ralph/ralph.sh (full loop, AFK)If UPDATE_MODE=0:
Ralph initialized! Next steps (run from terminal, NOT inside Claude Code): - Edit scripts/ralph/config.env to customize settings - ./scripts/ralph/ralph_once.sh (one iteration, observe) - ./scripts/ralph/ralph.sh (full loop, AFK) Maintenance: - Re-run /flow-next:ralph-init after plugin updates to refresh scripts - Uninstall (run manually): rm -rf scripts/ralph/
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
flow-next-impl-review
John Carmack-level implementation review via RepoPrompt or Codex. Use when reviewing code changes, PRs, or implementations. Triggers on /flow-next:impl-review.
flow-next
Manage .flow/ tasks and epics. Triggers: 'show me my tasks', 'list epics', 'what tasks are there', 'add a task', 'create task', 'what's ready', 'task status', 'show fn-1-add-oauth'. NOT for /flow-next:plan or /flow-next:work.
flow-next-plan
Create structured build plans from feature requests or Flow IDs. Use when planning features or designing implementation. Triggers on /flow-next:plan with text descriptions or Flow IDs (fn-1-add-oauth, fn-1-add-oauth.2, or legacy fn-1, fn-1.2, fn-1-xxx, fn-1-xxx.2).
flow-next-worktree-kit
Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.
flow-next-rp-explorer
Token-efficient codebase exploration using RepoPrompt CLI. Use when user says "use rp to..." or "use repoprompt to..." followed by explore, find, understand, search, or similar actions.
flow-next-deps
Show epic dependency graph and execution order. Use when asking 'what's blocking what', 'execution order', 'dependency graph', 'what order should epics run', 'critical path', 'which epics can run in parallel'.
Didn't find tool you were looking for?