القائمة
Run an ito ralph loop for a change, module, or repo-ready sequence, with safe defaults and automatic restart context on early exits.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Implement Ito Lite markdown changes by reading proposal/spec/design/tasks artifacts and updating manual task statuses. Use when applying or executing a prompt-only Ito Lite change without the ito CLI.
Archive completed Ito Lite changes by manually merging spec deltas into current specs and moving the change to archive. Use after implementation and verification when no ito CLI is available.
Create prompt-driven Ito Lite change proposal packages in markdown. Use for drafting proposal.md, spec deltas, optional design.md, and tasks.md without the ito CLI or validation executable.
Review Ito Lite markdown proposal packages before implementation. Use to check proposal.md, spec deltas, design.md, and tasks.md for consistency, risk, testability, and manual validation without the ito CLI.
Initialize a markdown-only Ito Lite workspace with no executables. Use when setting up prompt-driven change proposals, creating .ito-lite/project.md, or preparing a repo for Ito-style specs, changes, and tasks without the ito CLI.
Coordinate the prompt-only Ito Lite workflow for proposals, specs, tasks, reviews, implementation, and archive without the ito executable. Use when the user asks for Ito-style planning, change proposals, lightweight specs, or markdown-only change management.
| name | ito-loop |
| description | Run an ito ralph loop for a change, module, or repo-ready sequence, with safe defaults and automatic restart context on early exits. |
Run ito ralph for one change, one module, or the next ready work item, with safe defaults and bounded restarts.
Parse /ito-loop arguments into one of these modes:
| Input | Mode | Command shape |
|---|---|---|
^[0-9]{3}-[0-9]{2}_[a-z0-9-]+$ | change | ito ralph ... --change <id> |
^[0-9]{3}$ | module | ito ralph ... --module <id> |
next, continue, natural language for next ready work, or empty | continue-ready | ito ralph ... --continue-ready |
--model <model-id>--max-iterations <n>--timeout <duration> (e.g. 15m)opencode, claude, codex, copilot, or pi)Parse input with ito util parse-id $ARGUMENTS:
parsed=$(ito util parse-id $ARGUMENTS)
mode=$(echo "$parsed" | jq -r '.mode')
id=$(echo "$parsed" | jq -r '.id // empty')
mode will be change, module, or continue-ready.id is set for change and module modes; empty for continue-ready.eval, and always quote variables.Choose the active harness.
Build one base ito ralph command. Ralph already manages its own internal loop, so do not wrap it in an unbounded retry loop.
Command shapes:
# Mode: change
ito ralph --no-interactive --harness <harness> --change <change-id> --max-iterations 5 --timeout 15m
# Mode: module
ito ralph --no-interactive --harness <harness> --module <module-id> --max-iterations 5 --timeout 15m
# Mode: continue-ready
ito ralph --no-interactive --harness <harness> --continue-ready --max-iterations 5 --timeout 15m
Apply any user-provided overrides on top of the defaults. Check ito ralph --help only if extra flags matter.
Run the command once.
0: report success and stop.For each bounded restart, collect context from:
ito ralph --no-interactive --change <change-id> --status
ito tasks status <change-id>
Summarize the context into a short restart note containing:
You have been restarted ...Append it before the rerun:
ito ralph --no-interactive --change <change-id> --add-context "<restart-note>"
Re-run the same base command.
After the supervised run sequence finishes:
ito ralph --status and ito tasks status are meaningful.