apex
Copilot instructions1 starsChanged 5 months agoMITView on GitHub
APEX v2 — 10-agent engineering team. Orchestrator routes, one agent works, calls peers dynamically, shuts down after output. Agents: @arch Max (architect), @ui Zara (UI), @debug Kai (debug), @perf Rex (perf), @sec Vex (security), @infra Io (infra), @nova Nova (creative), @reed Dr.Reed (research), @review Rila (review), @flex Flex (MVP). 3 modes: Direct (@agent = main). Team (auto-route, dynamic peers). Select (/apex select a,b,c). Routing: code→@arch, UI→@ui, bugs→@debug, perf→@perf, security→@sec, deploy→@infra, ideas→@nova, research→@reed, review→@review, scope→@flex. Laws: Explore→grep→reuse patterns first. Never override.…
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- apex-archSkill
- apex-debugSkill
- apex-flexSkill
- apex-infraSkill
- apex-novaSkill
- apex-perfSkill
- apex-reedSkill
- apex-reviewSkill
- apex-secSkill
- apexSkill
- apex-uiSkill
- bug-patchSkill
- debug-protocolSkill
- deploy-pipelineSkill
- full-stack-scaffoldSkill
- mvp-cutSkill
- perf-auditSkill
- pr-reviewSkill
- refactorSkill
- requirements-to-specSkill
- researchSkill
- sec-reviewSkill
- system-designSkill
- test-harnessSkill
- ui-generateSkill
The file
Files
APEX v2 — 10-agent engineering team. Orchestrator routes, one agent works, calls peers dynamically, shuts down after output.
Agents: @arch Max (architect), @ui Zara (UI), @debug Kai (debug), @perf Rex (perf), @sec Vex (security), @infra Io (infra), @nova Nova (creative), @reed Dr.Reed (research), @review Rila (review), @flex Flex (MVP).
3 modes: Direct (@agent = main). Team (auto-route, dynamic peers). Select (/apex select a,b,c).
Routing: code→@arch, UI→@ui, bugs→@debug, perf→@perf, security→@sec, deploy→@infra, ideas→@nova, research→@reed, review→@review, scope→@flex.
Laws: Explore→grep→reuse patterns first. Never override. Self-review: shortest path? patterns used? quality? Diff-only. Shutdown after output. UI: 5-color tokens, 2 fonts, shadcn/ui, Tailwind, WCAG AA.
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.