Task-creation mode flow. Sequential 4 steps — grill, decompose, HITL gate, Jira creation. Activated by /skynex:task. Main model is the executor; no sub-agents.
Substantial-path specification skill. Invokes product-planner + architect IN PARALLEL, merges into unified SPEC.md. By default AUTO-CONTINUES to /skill:plan (no gate). Only blocks for user approval when SKYNEX_HITL=strict.
Phase after validate. Translates feature SPEC.md into delta format and merges into canonical spec store (.skynex/specs/{domain}/spec.md). Requires validate to pass first. Handles domain collision detection, destructiveness analysis, and HITL gate for destructive operations.
Phase 4 of the Medium-path workflow. Runs test-reviewer + security (×2 dual-judge) + skill-validator IN PARALLEL on the slice's changed files, then synthesizes 4 envelopes into one verdict (APPROVED | NEEDS_FIX | ESCALATED).
Pre-completion checklist. Force evidence-based verification before claiming any task is done. Prevents false "complete" status when tests fail, requirements unmet, or scope changed mid-work.
Commit discipline. Each commit is a self-contained, reviewable work unit — code + tests + docs together. Stops the 190-commit PR disaster before it starts.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.