multica-ops
01Plugin Claude Code
Plugin marketplace listing 1 plugin: multica-ops.
Plugin Claude Code
Plugin marketplace listing 1 plugin: multica-ops.
Plugin Claude Code
Mops (Executive Advisor) for Multica: builds and runs an autonomous company of AI agents — interview, bootstrap, conveyor, console.
Instructions file CodexOpenCode
Instructions for jamillazarev/multica-ops, covering agent entry point, changing this repository? read this part, before building anything: does multica already do it?, when a flow deserves a command — and how one appears and writing the changelog.
Instructions file
Instructions for jamillazarev/multica-ops, covering this is the skill's own repository, the session loop, versioning and machine notes.
Instructions file Gemini CLI
Instructions for jamillazarev/multica-ops: This workspace has the multica-ops extension installed. Before acting as Mops — or on any request about building or running a company of AI agents on Multica, a project, features, roles or budgets — read skills/mops/SKILL.md and follow it. The hard gates that must survive…
Hook Claude Code
Runs before the agent uses a tool for Edit and Write tool calls, executing decisions-guard.sh via bash. From jamillazarev/multica-ops.
Settings file Claude Code
Agent settings declaring 1 hook event (PreToolUse).
Hook
Runs when a session starts, executing migration-state.sh. From jamillazarev/multica-ops.
Hook
Runs after a tool call finishes, executing dispatch-nudge.sh. From jamillazarev/multica-ops.
Skill Claude CodeCodex
Health and opportunities: what burns tokens, what stalls, what drifted, and what the ledger counts as waste.
Skill Claude CodeCodex
The urgent lane that jumps the queue — a defect, recall or correction, reproduced before it is fixed.
Skill Claude CodeCodex
Raw Multica CLI — run or explain any multica … command directly, no methodology assumed.
Skill Claude CodeCodex
A question, not a build: answered as an advisor, with nothing created in your workspace.
Skill Claude CodeCodex
Add a feature mid-flight — grilled into a spec, ICE-scored against the backlog, slotted into a release.
Skill Claude CodeCodex
Offboard an agent or a person — what they own and block surfaces first, then reassignment, then the archive.
Skill Claude CodeCodex
Grow the team — an agent built by the role-builder, or a real person by invitation.
Skill Claude CodeCodex
Bring a backlog in from another tracker — the mapping is shown first, and issues arrive unassigned.
Skill Claude CodeCodex
Stand a company up from zero: day zero checks, a progressive interview, then the team.
Skill Claude CodeCodex
Take over an existing workspace — audited before anything is touched, then fixed in batches you approve.
Skill Claude CodeCodex
Use when the user wants to build, bootstrap, join, or operate an autonomous team of AI agents on Multica — you act as their Mops (Executive Advisor); interview them progressively (defaults everywhere, small tasks stay small), create everything via the CLI (workspace-as-company, conductor/PM, agents, squads, skills…
Skill Claude CodeCodex
Start the next feature from the roadmap — the manual flow's main button.
Skill Claude CodeCodex
One job, no company: three questions, one or two agents, build then review.
Skill Claude CodeCodex
Revive after a session limit — interrupted work reruns and resumes rather than restarting.
Skill Claude CodeCodex
Something went wrong or made the work harder — recorded where it belongs, and if it is the skill's own defect, packaged into a file you can send.