Skip to content
Agent Orchestration
Command

/hep-local

Staff a task only from Agentlas agents registered on this machine.

From plugin
agentlas-os
1.5k45 skills6 agents45 commands2 MCP
> /plugin marketplace add agentlas-ai/Agentlas-OS
> /plugin install hephaestus@agentlas-core-engine

Command definition

hep-local.md
description: Staff a task only from Agentlas agents registered on this machine.
argument-hint: '<request>'
allowed-tools: Bash, Read, Glob, Grep

Update fallback: 자동 업데이트가 안 되면 `hephaestus update`를 한 번 실행하세요. 업데이트하지 않아도 현재 버전 명령은 그대로 동작합니다.

/hep-local

Raw request: `$ARGUMENTS`

Act as the temporary top-level workforce orchestrator. Use the local Agentlas OS MCP server `hephaestus-network` and call the Workforce tools with exact `sourceScope: "local"`. Before every unpinned discovery, Core refreshes the current safe snapshot for each active registered Local source, creating a new release when the source folder changed. This command searches only that registered Local inventory; it must not add owner Cloud or public Hub candidates. A prepared or goal-bound selection remains pinned to its exact release. `network reindex` rebuilds the card cache but is not the release refresh mechanism, and a new source still requires explicit registration.

1. Author a redacted `agentlas.workforce-work-order.v1`; private project grounding stays on-host. 2. Call `workforce.search_candidates` with `{workOrder, sourceScope: "local"}` and keep the complete response as `federationResult`, including its local registry receipt and the projected menu's `selectionSessionId`. Do not echo the projected menu back as `federationResult` — Core resolves the complete federation state locally from that session. 3. Author the final `agentlas.workforce-selection.v1` as the active host LLM, then call `workforce.validate_selection` with `{workOrder, selection}` and keep the response as `federatedSelection`. Revise on rejection; do not accept a deterministic picker or unrelated fallback. 4. Call `workforce.prepare_execution` with `{workOrder, selection, federatedSelection, projectDir}`. Require every selected row to remain pinned to source `local`, exact package/content identity, runtime bundle, permission policy, and context digest. 5. Execute distinct planner/manager, worker, synthesis, and verifier calls with explicit artifact handoffs. Preserve packaged Team graphs.

If the local Core MCP or registered inventory is unavailable, report `source_unavailable`; do not silently search Cloud or Hub. A prepared roster is not proof of execution.

If `workforce.prepare_execution` refuses with a `repair` object, the agent is broken, not absent. Say in plain words what `repair.meaning` says, offer the first `available` action in `repair.repair`, and run its `command` only after the user agrees. When a repair reports `reselectionRequired: true`, select again (`workforce.validate_selection`, then `workforce.prepare_execution`); never swap in a different agent without a new selection. A refusal that carries `alternates` lists other callable agents from the same search: present them as candidates and let the user or the selection step choose.

A search does not scan folders. It lists agents already registered or already in the owner's card store; the builder registers what it builds; a package you placed in the global agent folder by hand is registered by `hephaestus workforce local-autoregister`, which returns what the contract still wants as `advisories`. The command prints `refused` and `skipped` rows, which is where to look when an agent you built is missing from the menu.

For a `partial` or `failed` result, report each source receipt's exact `failureCode`. Never collapse several receipts into one, substitute a different code, or relabel the outcome.

Read more
@agentlas-ai
Ships withagentlas-os

An open-source AI agent OS inspired by OpenAI Dots, Meta Muse, Claude Duet, Nous Hermes, and Mem0. Built to lead entire projects rather than isolated prompts. Model-agnostic (BYOM) and native to Claude Code, Codex, Cursor, Antigravity, and Agentlas Desktop.

1.5k47 skills6 agents2 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
1.5k
Star history of agentlas-ai/Agentlas-OS on GitHub, a chart by star-history.com

Other commands on agentlas-os.

More commands from other plugins.

COMMAND_COMPLIANCE_REPORT

COMMAND_COMPLIANCE_REP…

Command

Reviewed all command files in `.claude/commands/analysis/` directory to ensure proper usage of: - `mcp__claude-flow__*` tools…

@ruvnet@ruvnetInstall Command
ask

ask

Command

This compatibility command keeps `/oh-my-claudecode:ask` available without loading the full `ask` skill description in every…

@yeachan-heo@yeachan-heoInstall Command