Menu
Use when user asks 'how is the run going', 'loop status', 'ralph status', 'what iteration', or /flow-code:loop-status.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Internal pipeline engine. Manages the entire pipeline (brainstorm, plan, plan-review, work, impl-review, close) via flowctl phase commands. Invoked by /flow-code:go.
Use when exploring requirements before planning. Pressure-tests ideas, generates approaches, and outputs a requirements doc for /flow-code:plan. Supports --auto mode for AI self-interview (no human input needed).
Use when exploring requirements before planning. Pressure-tests ideas, generates approaches, and outputs a requirements doc for /flow-code:plan.
Use when planning features or designing implementation. Triggers on /flow-code:plan with text descriptions or Flow IDs.
Use when reviewing code changes — self-review in Worker Phase 6, impl-review, or PR review. Applies five-axis scoring with severity labels.
Use when implementing a plan or working through a spec. Triggers on /flow-code:work with Flow IDs.
| name | flow-code-loop-status |
| description | Use when user asks 'how is the run going', 'loop status', 'ralph status', 'what iteration', or /flow-code:loop-status. |
| tier | 1 |
| user-invocable | false |
Shows the live status of running Ralph or auto-improve loops by reading status.json from the run directory. Non-blocking — does not interrupt the running loop.
Full request: $ARGUMENTS
| Param | Default | Description |
|---|---|---|
| type | auto-detect | ralph or auto-improve |
--run <id> | latest | Specific run ID to check |
Check both Ralph and auto-improve run directories for status.json:
# Ralph runs
RALPH_STATUS=""
for dir in scripts/ralph/runs/latest scripts/ralph/runs; do
if [[ -f "$dir/status.json" ]]; then
RALPH_STATUS="$dir/status.json"
break
fi
done
# Auto-improve runs
AI_STATUS=""
for dir in scripts/auto-improve/runs/latest scripts/auto-improve/runs; do
if [[ -f "$dir/status.json" ]]; then
AI_STATUS="$dir/status.json"
break
fi
done
If user specified --run <id>, look in that specific run directory instead.
For each found status.json, read the file and format output.
Ralph format:
Ralph Run: <run_id>
Phase: <phase> | Iteration: <iteration>/<max_iterations>
Current: <current_id> — "<current_title>"
Progress: <tasks_done>/<tasks_total> tasks | <epics_done>/<epics_total> epics
Review mode: <review_mode>
Git: <git_branch> | <git_stats>
Updated: <relative_time> ago
Auto-improve format:
Auto-Improve Run: <run_id>
Goal: <goal>
Scope: <scope>
Experiment: <experiment>/<max_experiments>
Results: <kept> kept | <discarded> discarded | <crashed> crashed
Success rate: <kept/(kept+discarded+crashed)*100>%
Git: <git_branch>
Updated: <relative_time> ago
If the run directory contains events.jsonl, show the last 5 events:
tail -5 "$RUN_DIR/events.jsonl" | python3 -c "
import json, sys
for line in sys.stdin:
try:
e = json.loads(line.strip())
ts = e.get('ts', '?')[-8:] # HH:MM:SS
event = e.get('event', '?')
extra = {k: v for k, v in e.items() if k not in ('ts', 'level', 'event')}
extra_str = ' '.join(f'{k}={v}' for k, v in extra.items())
print(f' {ts} {event} {extra_str}')
except: pass
"
If status.json shows phase complete or stopped, also check for summary.md and display it.
If no status.json found in either location:
No active loops found.
To start a loop:
Ralph: cd scripts/ralph && ./ralph.sh
Auto-improve: cd scripts/auto-improve && ./auto-improve.sh