yuri-sentinel
Always-on autonomous check daemon running natively in Musubi. Runs every 33min via LaunchAgent — proactive system health, memory pulse, external signal checks, vault alerts. The 09OC research lane is retired into @deepseek-flash.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- yuri-sentinel
- triggers
- [ "/yuri-sentinel", "/sentinel", "sentinel check", "sentinel status" ]
- description
- Always-on autonomous check daemon running natively in Musubi. Runs every 33min via LaunchAgent — proactive system health, memory pulse, external signal checks, vault alerts. The 09OC research lane is retired into @deepseek-flash.
- routing_note
- Yuri Sentinel runs autonomously. Use /sentinel to check its last state or trigger a manual run.
03 SKILL.md 正文
Yuri Sentinel — Always-On Autonomous Layer
Formerly OpenClaw 09OC / Nisaba Sentinel. Fully absorbed into Musubi as of 2026-05-17.
What it is
Not a CLI tool to call on. A persistent autonomous process that runs every 33 minutes via LaunchAgent, integrated into Musubi's native loop.
- Script:
Scripts/yuri-sentinel.mjs - LaunchAgent:
com.yuri.yuri-sentinel.plist(in~/Library/LaunchAgents/) - State:
.claude/state/yuri-sentinel-state.json - Alerts: appended to
.claude/state/pulse-vault-log/YYYY-MM-DD.md
What it checks every 33 minutes
- System health — pulse-plan.json, pulse-bus.json, hypotheses.json, CRITICAL bus entries
- Memory pulse — runs memory-consolidate.mjs (flags near-duplicates and contradictions)
- External signals — knowledge scout freshness, overdue neuron-loop detection
- Gate health — independence score, launch readiness checks
Manual trigger
node Scripts/yuri-sentinel.mjs
What happened to OpenClaw / 09OC / Nisaba?
The 09OC research lane → now just @deepseek-flash.
The daemon heartbeat → now yuri-sentinel.mjs + LaunchAgent.
The multi-model routing → in offload-contract.mjs.
The identity/SOUL → in SOUL.md.
The memory system → in semantic-memory.db.
The plugin system → in .claude/skills/.
Nothing was lost. Everything was absorbed.
Session Notes
2026-05-29
- session: 210m | peak ctx: 54% | compacts: 0
- tools: Bash×131, Read×93, Edit×92, TodoWrite×10, Write×7, StructuredOutput×5, ToolSearch×1, Workflow×1
- corrections: none
- errors: none
2026-05-17
- session: 161m | peak ctx: 0% | compacts: 0
- tools: Bash×196, mcp×71, Read×51, Edit×48, Write×12, WebFetch×12, ToolSearch×6, TodoWrite×2, ExitPlanMode×1
- corrections: screenshot 1: what is this recommendation, is it useful? if yes, i need yuri to provide inputs like that too. screenshot 2/3: done
i have run both gitnexus and push origin main commands in terminal
- errors: none
2026-05-17
- session: 160m | peak ctx: 0% | compacts: 0
- tools: Bash×196, mcp×71, Read×51, Edit×48, Write×12, WebFetch×12, ToolSearch×6, TodoWrite×2, ExitPlanMode×1
- corrections: screenshot 1: what is this recommendation, is it useful? if yes, i need yuri to provide inputs like that too. screenshot 2/3: done
i have run both gitnexus and push origin main commands in terminal
- errors: none
2026-05-17
- session: 154m | peak ctx: 0% | compacts: 0
- tools: Bash×180, mcp×71, Read×51, Edit×47, Write×12, WebFetch×12, ToolSearch×6, TodoWrite×2, ExitPlanMode×1
- corrections: screenshot 1: what is this recommendation, is it useful? if yes, i need yuri to provide inputs like that too. screenshot 2/3: done
i have run both gitnexus and push origin main commands in terminal
- errors: none
2026-05-17
- session: 153m | peak ctx: 0% | compacts: 0
- tools: Bash×180, mcp×71, Read×51, Edit×47, Write×12, WebFetch×12, ToolSearch×6, TodoWrite×2, ExitPlanMode×1
- corrections: screenshot 1: what is this recommendation, is it useful? if yes, i need yuri to provide inputs like that too. screenshot 2/3: done
i have run both gitnexus and push origin main commands in terminal
- errors: none
2026-05-17
- session: 141m | peak ctx: 0% | compacts: 0
- tools: Bash×159, mcp×71, Read×49, Edit×45, WebFetch×12, Write×11, ToolSearch×6, TodoWrite×2, ExitPlanMode×1
- corrections: screenshot 1: what is this recommendation, is it useful? if yes, i need yuri to provide inputs like that too. screenshot 2/3: done
i have run both gitnexus and push origin main commands in terminal
- errors: none
2026-05-17
- session: 124m | peak ctx: 0% | compacts: 0
- tools: Bash×124, mcp×71, Read×47, Edit×42, WebFetch×12, Write×10, ToolSearch×6, TodoWrite×2, ExitPlanMode×1
- corrections: none
- errors: none
2026-05-17
- session: 118m | peak ctx: 0% | compacts: 0
- tools: Bash×109, mcp×70, Read×44, Edit×41, WebFetch×12, Write×9, ToolSearch×6, TodoWrite×2, ExitPlanMode×1
- corrections: none
- errors: none
2026-05-17
- session: 116m | peak ctx: 0% | compacts: 0
- tools: Bash×109, mcp×70, Read×44, Edit×41, WebFetch×12, Write×9, ToolSearch×6, TodoWrite×2, ExitPlanMode×1
- corrections: none
- errors: none
2026-05-17
- session: 109m | peak ctx: 0% | compacts: 0
- tools: Bash×81, mcp×70, Read×40, Edit×39, WebFetch×12, Write×8, ToolSearch×6, TodoWrite×2, ExitPlanMode×1
- corrections: none
- errors: none
2026-05-17
- session: 107m | peak ctx: 0% | compacts: 0
- tools: Bash×80, mcp×70, Read×40, Edit×39, WebFetch×12, Write×8, ToolSearch×6, TodoWrite×2, ExitPlanMode×1
- corrections: none
- errors: none
2026-05-17
- Renamed from nisaba-sentinel → yuri-sentinel (naming overhaul sprint)
- Triggers updated: /nisaba-sentinel → /yuri-sentinel
- Script and LaunchAgent paths confirmed correct
04 同仓库更多 Skills
zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
yuri-shura
6-perspective adversarial review for high-stakes turns (architecture decisions, refactor planning, deployment review) — fans out architect, adversary (7-vector attack), maintainer, ops, product, and security perspectives in parallel, then consolidates. Use when user says 'review this decision', '/shura', 'adversarial review', 'what could go wrong', 'architecture review', or 'deployment review'.
yuri-sales-intelligence
Unified sales and outreach skill generating cold outreach openers, social selling sequences, objection rebuttals, and ad creative for any paid platform — multi-persona aware, adapting tone and offer frame to buyer type. Use when user says 'write a cold email', 'outreach sequence', 'objection handling', 'ad copy', or 'sales pitch'.
yuri-code-intelligence
Unified code quality intelligence layer that diagnoses code smells (Long Method, Feature Envy, design pattern issues), prescribes targeted Fowler refactoring techniques, and reviews code for security, performance, and clarity. Use when user says 'review this code', 'refactor this', 'what's wrong with this method', 'code smells', or 'clean this up'.
yuri-adw
Invoke when user asks to run the ADW loop / agentic engineering loop / software factory workflow.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment