flow-next-ralph-init
The flow-next-ralph-init skill scaffolds or updates a repo-local Ralph autonomous testing harness under scripts/ralph/ when triggered by the /flow-next:ralph-init command. It detects available code review backends, copies templates and executables from the plugin root, preserves existing configuration during updates, and sets appropriate file permissions on shell scripts and the flowctl binary.
git clone --depth 1 https://github.com/gmickel/flow-next /tmp/flow-next-ralph-init && cp -r /tmp/flow-next-ralph-init/plugins/flow-next/skills/flow-next-ralph-init ~/.claude/skills/flow-next-ralph-initSKILL.md
# Ralph init
Scaffold or update repo-local Ralph harness. Opt-in only.
## Preamble
The plugin root resolves once via the cross-platform env-var fallback (Droid uses `DROID_PLUGIN_ROOT`; Claude Code documents `CLAUDE_PLUGIN_ROOT` as its compat alias). Subsequent blocks use `$PLUGIN_ROOT`:
```bash
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}"
```
## Rules
- **Every write lands under `scripts/ralph/` in the current repo.** A file written anywhere else has broken this.
- If `scripts/ralph/` already exists, offer to update (preserves config.env).
- Copy templates from `templates/` into `scripts/ralph/` (includes `ralphctl.py` for pause/resume/stop/status).
- Copy `flowctl`, `flowctl.cmd`, `flowctl.py`, `flowctl_bootstrap.py`, `flowctl-help.txt`, and the `flowctl_tracker/` package (from `$PLUGIN_ROOT/scripts/`) and `pick-python.sh` (from `$PLUGIN_ROOT/scripts/lib/`) into `scripts/ralph/` — **flat, so the resolver lands at `scripts/ralph/pick-python.sh`** where `ralph.sh` and the hook wrapper source it. A `pick-python.sh` that landed under `scripts/ralph/lib/` has broken this.
- Set executable bit on `scripts/ralph/ralph.sh`, `scripts/ralph/ralph_once.sh`, `scripts/ralph/flowctl`, and `scripts/ralph/ralphctl.py`.
- **Hook registration is agent-driven skill prose only.** The plugin ships no hooks by default; you (the host agent) merge the guard entries into the project's host settings via Read+Edit, idempotently, without clobbering unrelated hooks. **The boundary is hard: there is no flowctl subcommand for hook install/remove/status and no hook machinery in Python.** A settings file whose hooks object now holds only flow-next entries, or a hook-install subcommand added to the CLI, has broken this.
## Workflow
1. Resolve repo root: `git rev-parse --show-toplevel`
2. Check if `scripts/ralph/` exists:
- If exists: ask "Update existing Ralph setup? (preserves config.env and runs/) [y/n]"
- If no: stop
- If yes: set UPDATE_MODE=1
- If not exists: set UPDATE_MODE=0
3. Detect available review backends (skip if UPDATE_MODE=1):
```bash
if command -v rpce-cli >/dev/null 2>&1 \
|| [ -x "$HOME/RepoPrompt/repoprompt_ce_cli" ] \
|| [ -x "$HOME/Library/Application Support/RepoPrompt CE/repoprompt_ce_cli" ] \
|| command -v rp-cli >/dev/null 2>&1; then HAVE_RP=1; else HAVE_RP=0; fi
HAVE_CODEX=$(which codex >/dev/null 2>&1 && echo 1 || echo 0)
HAVE_COPILOT=$(which copilot >/dev/null 2>&1 && echo 1 || echo 0)
HAVE_CURSOR=$(which cursor-agent >/dev/null 2>&1 && echo 1 || echo 0)
```
4. Determine review backend (skip if UPDATE_MODE=1):
- If several are available, ask the user (do NOT use AskUserQuestion tool).
Show only the options whose CLIs were detected:
```
Multiple review backends available. Which one?
a) RepoPrompt (macOS, visual builder)
b) Codex CLI (cross-platform, reviewer models via a Codex subscription)
c) GitHub Copilot CLI (cross-platform, Claude/GPT via Copilot)
d) Cursor CLI (cross-platform, runs cursor-agent; reviewer models via a Cursor subscription)
(Reply: "a", "rp", "b", "codex", "c", "copilot", "d", "cursor", or just tell me)
```
Wait for response. Default if empty/ambiguous: prefer `rp` > `codex` > `copilot` > `cursor`.
- If only the RepoPrompt CLI ladder resolves: use `rp`
- If only codex available: use `codex`
- If only copilot available: use `copilot`
- If only cursor-agent available: use `cursor`
- If none available: use `none`
5. Copy files using bash — **the copies run through `cp`, never the Write tool.** A template reproduced by writing its contents has broken this:
**If UPDATE_MODE=1 (updating):**
```bash
# Backup config.env
cp scripts/ralph/config.env /tmp/ralph-config-backup.env
# Update templates (preserves runs/)
cp "$PLUGIN_ROOT/skills/flow-next-ralph-init/templates/ralph.sh" scripts/ralph/
cp "$PLUGIN_ROOT/skills/flow-next-ralph-init/templates/ralph_once.sh" scripts/ralph/
cp "$PLUGIN_ROOT/skills/flow-next-ralph-init/templates/prompt_plan.md" scripts/ralph/
cp "$PLUGIN_ROOT/skills/flow-next-ralph-init/templates/prompt_work.md" scripts/ralph/
cp "$PLUGIN_ROOT/skills/flow-next-ralph-init/templates/prompt_completion.md" scripts/ralph/
cp "$PLUGIN_ROOT/skills/flow-next-ralph-init/templates/watch-filter.py" scripts/ralph/
cp "$PLUGIN_ROOT/skills/flow-next-ralph-init/templates/ralphctl.py" scripts/ralph/
cp "$PLUGIN_ROOT/scripts/flowctl" "$PLUGIN_ROOT/scripts/flowctl.cmd" "$PLUGIN_ROOT/scripts/flowctl.py" "$PLUGIN_ROOT/scripts/flowctl_bootstrap.py" "$PLUGIN_ROOT/scripts/flowctl-help.txt" "$PLUGIN_ROOT/scripts/lib/pick-python.sh" scripts/ralph/
rm -rf scripts/ralph/flowctl_tracker && cp -R "$PLUGIN_ROOT/scripts/flowctl_tracker" scripts/ralph/flowctl_tracker
# fn-139.5: verify the tracker package post-copy - fail loudly here, never
# later as an ImportError mid-run
python3 "$PLUGIN_ROOT/scripts/lib/verify_tracker_manifest.py" scripts/ralph
mkdir -p scripts/ralph/hooks
cp "$PLUGIN_ROOT/scripts/hooks/ralph-guard.py" "$PLUGIN_ROOT/scripts/hooks/ralph-guard" scripts/ralph/hooks/
chmod +x scripts/ralph/ralph.sh scripts/ralph/ralph_once.sh scripts/ralph/flowctl scripts/ralph/ralphctl.py scripts/ralph/hooks/ralph-guard.py scripts/ralph/hooks/ralph-guard
# Restore config.env
cp /tmp/ralph-config-backup.env scripts/ralph/config.env
```
**If UPDATE_MODE=0 (fresh install):**
```bash
mkdir -p scripts/ralph/runs scripts/ralph/hooks
cp -R "$PLUGIN_ROOT/skills/flow-next-ralph-init/templates/." scripts/ralph/
cp "$PLUGIN_ROOT/scripts/flowctl" "$PLUGIN_ROOT/scripts/flowctl.cmd" "$PLUGIN_ROOT/scripts/flowctl.py" "$PLUGIN_ROOT/scripts/flowctl_bootstrap.py" "$PLUGIN_ROOT/scripts/flowctl-help.txt" "$PLUGIN_ROOT/scripts/lib/pick-python.sh" scripts/ralph/
rm -rf scripts/ralph/flowctl_tracker && cp -R "$PLUGIN_ROOT/scripts/flowctl_tracker" scripts/ralph/flowctl_tracker
# fn-139Synthesize the current conversation context into a flow-next spec at `.flow/specs/<spec-id>.md` via `flowctl spec create + spec set-plan` — agent-native, source-tagged, with mandatory read-back before write. Triggers on /flow-next:capture, "capture spec", "lock down what we discussed", "make a spec from this conversation", "convert conversation to spec". Optional `mode:autofix` token runs without questions and requires `--yes` to commit. Optional `--rewrite <spec-id>` overwrites an existing spec; `--from-compacted-ok` overrides the incomplete-evidence refusal after compaction; `--override-strategy` proceeds despite a contradiction with an active STRATEGY.md track (and prompts to record the override as a decision); `--no-plan` sets the spec-level `no_plan` field after the write (explicit opt-in — never inferred).
Render a cognitive-aid PR body from flow-next state and open via gh. Triggers on /flow-next:make-pr with optional spec id and flags (--draft, --ready, --no-mermaid, --base <ref>, --memory, --dry-run). Auto-detects spec from current branch when no id given. NOT Ralph-blocked — autonomous loops can surface a draft PR for human review.
Audit `.flow/memory/` entries against the current codebase and decide Keep / Update / Consolidate / Replace / Delete / Harden per entry. Triggers on /flow-next:audit, "audit memory", "review memory", "refresh learnings", "sweep stale memory", "consolidate overlapping memory entries", "graduate a recurring lesson into a gate". Optional `mode:autofix` token in arguments runs without questions and marks ambiguous as stale (Harden is never auto-applied). Optional scope hint after the mode token (concept, category, module, or path) narrows what gets audited.
Show spec dependency graph and execution order. Use when asking 'what's blocking what', 'execution order', 'dependency graph', 'what order should specs run', 'critical path', 'which specs can run in parallel'.
Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview) reached via the Cua Driver / Computer Use. Detects the surface, picks the best available driver, degrades gracefully. Use to navigate sites, verify deployed UI, test web or desktop apps, capture baseline screenshots, drive a sign-in flow, scrape data, fill forms, run an e2e check, or inspect current page state. Triggers on "check the page", "verify UI", "test the site", "test this app", "drive the app", "automate this desktop app", "read docs at", "look up API", "visit URL", "browse", "screenshot", "scrape", "e2e test", "login flow", "capture baseline", "see how it looks", "inspect current", "before redesign", "Electron app", "native app".
[deprecated alias] Renamed to flow-next-spec-completion-review in flow-next 1.0 — invoke the new skill. Removed in 2.0.
Export RepoPrompt context to a markdown file for review with an external LLM (ChatGPT, Claude web, etc.). Use when you want Carmack-level review but prefer an external model. Triggers on "export context", "export for external review", "export plan for ChatGPT", "export impl review context", "review with an external model", "export review context".