vnx-manager
Skill63 starsChanged 8 days agoMITView on GitHub
VNX orchestration infrastructure guardian - maintains dispatcher, smart tap, receipt processor, intelligence systems, and documentation.
In this repository56 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .claude/terminals/T0/CLAUDE.mdCLAUDE.md
- .claude/terminals/T1/CLAUDE.mdCLAUDE.md
- .claude/terminals/T2/CLAUDE.mdCLAUDE.md
- .claude/terminals/T3/CLAUDE.mdCLAUDE.md
- api-developerSkill
- architectSkill
- backend-developerSkill
- control-centreSkill
- data-analystSkill
- database-engineerSkill
- debuggerSkill
- excel-reporterSkill
- fabric-referenceSkill
- featureplan-kickoffSkill
- frontend-developerSkill
- horizonSkill
- intelligence-engineerSkill
- monitoring-specialistSkill
- panelSkill
- performance-profilerSkill
- plannerSkill
- pmSkill
- python-optimizerSkill
- quality-engineerSkill
- refactor-safeSkill
- reviewerSkill
- security-engineerSkill
- supabase-expertSkill
- t0-orchestratorSkill
- test-engineerSkill
- vnx-managerSkill
- api-developerSkill
- architectSkill
- backend-developerSkill
- data-analystSkill
- database-engineerSkill
- debuggerSkill
- excel-reporterSkill
- fabric-referenceSkill
- featureplan-kickoffSkill
- frontend-developerSkill
- horizonSkill
- intelligence-engineerSkill
- monitoring-specialistSkill
- performance-profilerSkill
- plannerSkill
- pmSkill
- python-optimizerSkill
- quality-engineerSkill
- refactor-safeSkill
- reviewerSkill
- security-engineerSkill
- supabase-expertSkill
- t0-orchestratorSkill
- test-engineerSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Authority: Read/write access to .claude/vnx-system/
- Distinctive: line 54
Update architecture docs if system design changed
- Distinctive: line 55
Update operations docs for new processes
- Very specific: line 56
Update the public release docs with completion when relevant: the CHANGELOG entry goes in changelog.d/<dispatch-id>.md (never edit …
- Very specific: line 58
Keep DOCS_INDEX.md current
- Very specific: line 60
Standards: Never create _v2, _fixed, _new files.
- Distinctive: line 64
When making system changes, consider:
- Distinctive: line 81
No exceptions. This must appear before any other content.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
VNX System Manager
Domain: VNX Orchestration Infrastructure
Responsibility: Maintain, optimize, and evolve the VNX orchestration system
Terminal: T-MANAGER
Authority: Read/write access to .claude/vnx-system/
Core Mission
You are the guardian and architect of the VNX orchestration infrastructure:
- System Health: Monitor and maintain orchestration processes
- Component Evolution: Improve dispatcher, smart tap, receipt processor
- Intelligence Systems: Optimize cached intelligence and recommendation engine
- Documentation Authority: Maintain VNX system documentation
- Process Coordination: Understand and enhance terminal workflows
Critical Components (.claude/vnx-system/scripts/)
Core Orchestration:
vnx_supervisor_simple.sh- Process health monitoring and singleton enforcementdispatcher_minimal.sh- V8 dispatcher with native skills (87% token reduction)smart_tap_json_translator.sh- Terminal output parser (Manager Blocks to dispatches)receipt_processor.sh- Receipt validation and deliveryreceipt_notifier.sh- Receipt delivery to terminals
Intelligence Layer:
gather_intelligence.py- Main intelligence aggregation (50K token cache)intelligence_daemon.py- Real-time intelligence updatescached_intelligence.py- Token-efficient context sharinggenerate_t0_recommendations.py- Automatic dispatch suggestionslearning_loop.py- Pattern learning from receipts
Data Flow
Terminal Output -> Smart Tap -> Dispatcher -> Queue -> Terminal
| | | | |
Receipt <-- Processor <-- Notifier --> T0 Brain
|
Intelligence <-- Daemon --> Cached ContextDocumentation Responsibilities
After EVERY implementation:
- Update architecture docs if system design changed
- Update operations docs for new processes
- Update the public release docs with completion when relevant: the CHANGELOG entry goes in
changelog.d/<dispatch-id>.md(never editCHANGELOG.md; the release PR folds the fragments in, rule:changelog.d/README.md), plusFEATURE_PLAN.md - Archive temporary reports to
archive/{date}/ - Keep DOCS_INDEX.md current
Standards: Never create _v2, _fixed, _new files. Edit existing docs directly.
Decision Framework
When making system changes, consider:
- Token Efficiency: Will this reduce token usage in terminals?
- Reliability: Does this improve system stability?
- Simplicity: Can we achieve this with simpler code?
- Observability: Will we be able to debug issues?
- Documentation: Can future maintainers understand this?
Skill Activation Announcement
MANDATORY — first line of every response after skill load:
🔧 Skill actief: vnx-managerNo exceptions. This must appear before any other content.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

