القائمة
Run an ito ralph loop for a specific change (or module/repo 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
Manage remote Kocao agent sessions from an AI assistant. Use when: listing running agents, starting a new remote agent, checking agent status, viewing agent logs, stopping an agent session, or sending a prompt to a running remote agent.
Fast trigram-indexed code search across the entire repository using Zoekt (the engine behind GitHub and Sourcegraph code search). Use INSTEAD OF grep/ripgrep for broad codebase searches. Supports regex, literal strings, file filters, and symbol queries. Auto-installs zoekt binaries and auto-indexes the repo on first use.
Apply a Change Proposal. Triggered by the user saying "Apply change <change-id>" or "Implement change <change-id>". Use when implementing, executing, applying, building, coding, or developing a feature, change, requirement, enhancement, fix, or modification. Use when running tasks from a spec, proposal, or plan.
You MUST use this before any creative work - creating features, proposing changes,building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work — presents structured options for merge, PR, or cleanup
Use when creating and writing an Ito change proposal (new change or existing change id). Delegates to Ito CLI instruction artifacts.
| name | ito-loop |
| description | Run an ito ralph loop for a specific change (or module/repo sequence), with safe defaults and automatic restart context on early exits. |
Run the Ito Ralph loop for a specific change (or module/repo sequence), with safe defaults and automatic restart context on early exits.
The user invokes this skill with /ito-loop followed by arguments. You must parse the arguments to determine which mode to use.
| Input pattern | What it is | Example invocations |
|---|---|---|
A full change id (matches ^[0-9]{3}-[0-9]{2}_[a-z0-9-]+$) | Change ID | /ito-loop 005-01_add-auth |
A short numeric id (matches ^[0-9]{3}$) | Module ID | /ito-loop 012, /ito-loop 005 |
| Words implying "pick the next ready change" | Continue-ready mode | /ito-loop next, /ito-loop continue, /ito-loop pick next ready |
| No arguments / empty | Continue-ready mode (default) | /ito-loop |
--model <model-id>--max-iterations <n>--timeout <duration> (e.g. 15m)Below are verbose examples showing exactly how user input maps to the ito ralph command. Study these carefully.
Example 1 — Change ID provided:
User input: /ito-loop 005-01_add-auth
Detected: Change ID → "005-01_add-auth"
Command: ito ralph --no-interactive --harness opencode --change 005-01_add-auth --max-iterations 5 --timeout 15m
Example 2 — Module ID provided (3-digit number):
User input: /ito-loop 012
Detected: Module ID → "012"
Command: ito ralph --no-interactive --harness opencode --module 012 --max-iterations 5 --timeout 15m
Note: --module in --no-interactive mode implies --continue-module, so ralph will work through all ready changes in that module.
Example 3 — Module ID with extra flags:
User input: /ito-loop 005 --model claude-sonnet-4-20250514 --max-iterations 10
Detected: Module ID → "005", model override, iteration override
Command: ito ralph --no-interactive --harness opencode --module 005 --model claude-sonnet-4-20250514 --max-iterations 10 --timeout 15m
Example 4 — "Next ready" / continue-ready (explicit):
User input: /ito-loop next
Detected: Continue-ready mode (keyword: "next")
Command: ito ralph --no-interactive --harness opencode --continue-ready --max-iterations 5 --timeout 15m
Example 5 — No arguments (implicit continue-ready):
User input: /ito-loop
Detected: No arguments → default to continue-ready mode
Command: ito ralph --no-interactive --harness opencode --continue-ready --max-iterations 5 --timeout 15m
Example 6 — Natural language implying ready work:
User input: /ito-loop pick up the next thing that needs doing
Detected: Continue-ready mode (natural language intent)
Command: ito ralph --no-interactive --harness opencode --continue-ready --max-iterations 5 --timeout 15m
Example 7 — Change ID with timeout override:
User input: /ito-loop 003-02_fix-login --timeout 30m
Detected: Change ID → "003-02_fix-login", timeout override
Command: ito ralph --no-interactive --harness opencode --change 003-02_fix-login --max-iterations 5 --timeout 30m
opencode).ito ralph --status + ito tasks status.Parse the input by running ito util parse-id $ARGUMENTS and reading the JSON output:
parsed=$(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 harness:
claude, codex, copilot, opencode or pi).Build and run a single ito ralph command.
Ralph already runs an iterative loop internally — do NOT wrap it in another retry loop or bash while-loop. Just run the one command and let Ralph manage iterations, timeouts, and completion detection.
Depending on the detected mode, the command looks like one of:
# 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 (--model, --max-iterations, --timeout)
on top of the defaults.
Check ito ralph --help for additional flags that might be relevant.
After Ralph exits:
/ito-loop to resume.