Fearvox/multica-ultimate-workbench
Instructions file GitHub Copilot
Copilot instructions for Fearvox/multica-ultimate-workbench: This repository uses local browser and MCP tools in some human-operated workflows, but GitHub Copilot, Codex Cloud, and repo-reply bots must run with a cloud-safe profile.
Fearvox/multica-ultimate-workbench
Instructions file CodexOpenCode
AGENTS.md instructions for Fearvox/multica-ultimate-workbench, covering agents.md, read order, repository role, codex app supervisor session and operating rules.
Fearvox/multica-ultimate-workbench
Instructions file
Claude Code instructions for Fearvox/multica-ultimate-workbench, covering claude.md, mission, codex app supervisor session, read order and hard boundaries.
Fearvox/multica-ultimate-workbench
Agent
Workbench Admin owns Friction Tier selection at intake.
Fearvox/multica-ultimate-workbench
Agent
This is a public-safe template. Keep live workspace IDs, runtime IDs, and generated command transcripts in the ignored file.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Use when syncing skills, MCPs, or AGENTS.md sections across coding agents with agent-install.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Advisory-only algorithm and data-structure review gate between Technical Design and Task List.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Browser verification, proof screenshots, traces, console and network checks, and reproducible UI evidence for Workbench QA.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Source-first, self-loop resistant guardrails for Capy GitHub dialogue responders before any write-capable PR, issue, or review action.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Use when checking live Capy task or PR state through Brave, Computer Use, or a Capy browser panel.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Controlled VM/Computer execution lane for GUI, browser, sandbox, and screenshot-backed tasks.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Strict parser and validator for Workbench closeout comments, verdict/status discipline, PR reference types, and cross-issue REMAINING sync.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Findings-first review discipline for code, diffs, task plans, live workflow changes, and implementation evidence.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Two-ring orchestration, routing, issue and comment discipline, and role boundaries for the Multica Workbench.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Root-cause investigation for bugs, regressions, suspicious runtime behavior, failed automations, and unexpected outcomes.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Product design, technical design documents, user-facing copy, specs, diagrams, and handoff documentation.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Post-change documentation sync for decisions, synthesis, skill maps, release notes, and durable handoffs.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Deployable Flue agent harness lane for HTTP, CI, Node, Cloudflare, and sandbox-backed agents.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Frontend and visual QA for responsive surfaces, screenshots, text fit, hierarchy, and interaction states.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
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.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Goal-persistence execution wrapper for autonomous work that must continue across turns until the stated objective is actually satisfied.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Owner-scoped task decomposition with gates, rollback, verification commands, and smoke tests.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
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.
Fearvox/multica-ultimate-workbench
Skill Claude CodeCodex
Minimal-patch implementation, ops changes, scripts, automation specs, and local repository edits.