apex-unified
AGENTS.md0 starsChanged 4 months agoMITView on GitHub
explore → discuss → plan → execute → build → verify → ship Each phase generates a different AI prompt. Mode-specific skills and agents are automatically injected. 38 skills auto-discovered from skills/ directory. New skills are automatically cached and phase-injected — no configuration needed.
In this repository39 other files it gives its agents.
- apex-modeSkill
- apex-specSkill
- api-designSkill
- architecture-decision-recordsSkill
- backend-patternsSkill
- brainstormingSkill
- coding-standardsSkill
- database-migrationsSkill
- delivery-gateSkill
- deployment-patternsSkill
- dispatching-parallel-agentsSkill
- docker-patternsSkill
- error-handlingSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- frontend-patternsSkill
- gateguardSkill
- git-workflowSkill
- pi-integrationSkill
- plan-orchestrateSkill
- postgres-patternsSkill
- prdSkill
- python-testingSkill
- ralphSkill
- react-patternsSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- safety-guardSkill
- sdk-scanSkill
- security-reviewSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- tdd-workflowSkill
- test-driven-developmentSkill
- using-git-worktreesSkill
- verification-before-completionSkill
- verification-loopSkill
- writing-plansSkill
- writing-skillsSkill
The file
Files
apex-unified Agent Instructions
Slash Commands
/apex:status— Show project status (current mode, active skills/agents, phases, model, AI tool)/apex:plan [phase]— Show phase prompt for the specified phase (explore, discuss, plan, execute, build, verify, ship). Defaults to discuss phase./apex:review— Show code review agent prompt with current mode's skills and agents/apex:detect <text>— Auto-detect and switch mode from natural language input/apex:spec init|propose|list|archive— Spec-driven development workflow
Modes
daily-dev— Bug fixes, small features (7 skills, 3 agents)full-stack— Full-stack web applications (9 skills, 5 agents)deep-research— Architecture analysis, security review (9 skills, 5 agents)spec-mode— Spec-first development (5 skills, 5 agents)embedded-dev— ESP32/Arduino firmware development (7 skills, 4 agents)
Phases
explore → discuss → plan → execute → build → verify → ship
Each phase generates a different AI prompt. Mode-specific skills and agents are automatically injected.
Skills
38 skills auto-discovered from skills/ directory. New skills are automatically cached and phase-injected — no configuration needed.
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.