multica-ultimate-workbench

Strict parser and validator for Workbench closeout comments, verdict/status discipline, PR reference types, and cross-issue REMAINING sync.

Scout, pilot, or review Mirage virtual-filesystem tool use for Workbench agents while preserving source-of-truth and public-safety boundaries.

Source-first, self-loop resistant guardrails for Capy GitHub dialogue responders before any write-capable PR, issue, or review action.

Disk, swap, VM, agent workspace, and stale session hygiene for Multica workbench runtimes.

Advisory-only algorithm and data-structure review gate between Technical Design and Task List.

Durable memory, session summaries, decision logs, issue closeout synthesis, and compact handoffs.

Use when an operator asks what changed recently, what was left hanging, what can move now, "gm", "where are we", or when a session-derived update needs to become visible to the whole Workbench. Recall recent memory, verify live repo/issue/automation state, surface drift first, and produce a short evidence-labeled action menu.

Use when upgrading a public GitHub repository README, repo metadata, docs map, or first-impression brand surface to match the Zonic/Evensong proof-first standard.

Use when Hermes reviews Claude-authored writeups, public docs, skill changes, README/agent/issue-template changes, or upstream speed-match documentation before syncing or publishing.

Horizontal session personality overlay — auto-detects conversation mode from density signals, defaults casual, upgrades to structured only on sustained signal. Includes CommitMono aesthetic preference and MoE/thinking-chain runtime awareness.

Two-ring orchestration, routing, issue and comment discipline, and role boundaries for the Multica Workbench.

Two-layer autonomous conductor — design loop produces decision packets, dispatch loop routes to bounded issues with dedupe/cooldown/archive controls. Replaces v1's single-agent persistence with a durable control loop that stops only at real blockers.

Capability discovery and current-state verification for Heavy Path, ambiguous repo/runtime ownership, and runtime-dependent Standard Path work.

Use when syncing skills, MCPs, or AGENTS.md sections across coding agents with agent-install.

Browser verification, proof screenshots, traces, console and network checks, and reproducible UI evidence for Workbench QA.

Use when checking live Capy task or PR state through Brave, Computer Use, or a Capy browser panel.

Controlled VM/Computer execution lane for GUI, browser, sandbox, and screenshot-backed tasks.

Findings-first review discipline for code, diffs, task plans, live workflow changes, and implementation evidence.

Root-cause investigation for bugs, regressions, suspicious runtime behavior, failed automations, and unexpected outcomes.

Product design, technical design documents, user-facing copy, specs, diagrams, and handoff documentation.

Post-change documentation sync for decisions, synthesis, skill maps, release notes, and durable handoffs.

Deployable Flue agent harness lane for HTTP, CI, Node, Cloudflare, and sandbox-backed agents.

Frontend and visual QA for responsive surfaces, screenshots, text fit, hierarchy, and interaction states.

Goal-persistence execution wrapper for autonomous work that must continue across turns until the stated objective is actually satisfied.

Owner-scoped task decomposition with gates, rollback, verification commands, and smoke tests.

Minimal-patch implementation, ops changes, scripts, automation specs, and local repository edits.

Research Vault pressure gate for remote Hermes, VM, HarnessMax, and autonomous evolution sweeps.

Bounded product ideation, workflow design, ambition checks, tradeoffs, and smallest-test shaping.

Evidence-first research, architecture discovery, vendor documentation review, benchmark reading, and unknown-system analysis.

PASS, FLAG, and BLOCK review discipline for workflow review, QA verification, release checks, and issue closeout.

Use when designing, reviewing, or updating Sanity as the shared context registry for workbench agents and CLIs.

Specification-driven development from raw requirement to product design, technical design, task list, execution, and verification.

Compact context, cache-aware execution, scoped evidence reads, and role-specific skill attachment discipline.