BYAN — Builder of YAN. Core meta-agent that owns the Feature Development (FD) workflow : DISCOVERY → BRAINSTORM → PRUNE → DISPATCH → BUILD → REVIEW → VALIDATE → DOC (with REFACTOR loop). Invoke whenever the user says "FD", "feature development", "nouvelle feature", "adapter <X>", "@byan", "@bmad", or mentions any BYAN menu command (INT/QC/EA/VA/DA/LA/PC/MAN/PM). Applies Merise Agile + TDD + 71 mantras. Owns recruitment (agent creation via INT); delegates execution of BUILD to byan-hermes-dispatch. Enforces phase gates — no phase is skipped, each requires explicit user validation before the next.
OpenCode/Codex integration specialist for BYAN skills Role: OpenCode/Codex Expert + Skills Integration Specialist.
BYAN local project skill. Use when working in the BYAN repo, invoking BYAN agents/workflows/commands, enforcing BYAN Strict Mode, or needing the portable BYAN filesystem map.
Autonomous BYAN dispatcher. Given a user task or a BYAN command result (like "execute FD on feature X"), this skill picks the right specialist agent from the BYAN roster, picks the right execution strategy and model via byan_dispatch (MCP), and spawns the work via the Agent tool without asking for confirmation. Invoke this whenever BYAN or the user describes work that needs to be delegated, or whenever the user says "@hermes <task>".
Enforcement mode that prevents scope downgrade and forces the agent to self-verify its work against the originally locked request before delivering. Invoke when the user asks for a production deliverable, a complete app, a filled contract from a template, or uses any activation keyword (`prod`, `production`, `client`, `contrat`, `template officiel`, `livrable`, `deliverable`, `mise en production`, `release`). Enforces scope-lock, N>=3 self-verify passes, and a 95% confidence floor on hard claims.
Fact-check scientifique BYAN (Demonstrable, Quantifiable, Reproductible). Invoquer quand un claim technique est fait, quand l'utilisateur utilise des absolus (toujours/jamais/obviously/faster/better), quand on audite un document, ou pour evaluer une chaine de raisonnement. Applique les 4 types d'assertions (REASONING/HYPOTHESIS/CLAIM Ln/FACT) et 5 niveaux de preuve. Domaines stricts (security/performance/compliance) = LEVEL-2 minimum.
Orchestrate a complex multi-role task across the BYAN roster with token-optimal model assignment and parallel execution. Use when a single task decomposes into 2+ distinct roles (e.g. "design + code + test", "analyst + architect + dev"), when you want to run BMAD specialists in parallel, or when you need a structured plan with per-role model choice before spawning. Extends byan-hermes-dispatch from 1-shot to N-role workflows. Keyword triggers : orchestrate, multi-role, team, BMAD team, advanced workflow.
Orchestrating conductor for the native byan-benchmark engine. Detects a real decision fork (>=2 non-substitutable options that diverge on >=1 weighted criterion), runs the autonomous DATA-only matrix engine (.claude/workflows/byan-benchmark.js) via the Workflow tool, renders the compact 1-table best-first, and emits the BYAN-BENCH marker so the auto-benchmark Stop hook is satisfied. Invoke when you are about to present a choice between options, when the user says "benchmark X vs Y", "compare these approaches", "which option", or when the auto-benchmark doctrine arms on a fork.