agentlas-ai/agentlas-os-openclaw-hephaestus-network
Use when the user asks OpenClaw to staff a durable goal from Agentlas Hub agents or teams. The active host LLM chooses the exact roster, which remains goal-bound until explicit completion.
npx skills add https://github.com/agentlas-ai/Agentlas-OS --skill hephaestus-network
The active host LLM is the per-turn orchestrator. Hub supplies content and
qualification evidence, exact immutable releases, and BYOM directives; it does
not select the final team or run a server-side LLM.
agentlas.workforce-work-order.v1 with substantive roleslots, skills/knowledge, MCP tools, artifacts, runtime/language/authority,
cardinality, and handoff/review edges. Keep private context local.
workforce.search_candidates.agentlas.workforce-selection.v1 from exact contentand eval evidence. Do not use lexical top-1, popularity, ratings, history,
revenue, or local callability as semantic fit.
workforce.validate_selection, revise on rejection, then callworkforce.prepare_execution. Require exact release version, package hash,
content digest, and directive bundle; never silently substitute.
workforce.bind_goal. On every later turn read workforce.goal_context,
reuse the incumbent roster plus local skills when sufficient, recruit only
a real additive gap, and record the posture with
workforce.record_goal_turn.
advertise the host's real sessions and call model.resolve_allocation with
the host-owned stage. Use the exact provider/model/effort receipt. Pins and
ceilings come only from AGENTLAS_MODEL_ALLOCATION_POLICY_JSON; missing
worker policy inherits orchestrator. usage: null before invocation is not
worker-execution proof.
distinct model invocations with explicit artifact handoffs and nested Team
graphs.
Keep the roster across turns, sessions, restarts, compaction, and lease expiry.
Release it only with workforce.complete_goal(explicitCompletion=true) after
explicit whole-goal completion/cancellation. A 24-hour lease controls only the
next Hub charge; standby is durable availability, not a continuously running
model. Memory/Experience accrue on actual invocations.
If this OpenClaw host cannot call the Workforce MCP tools or create separate child
invocations, report the last truthful state instead of calling the legacy
router. Execution success requires planner parse success without fallback,
every child/handoff receipt, synthesis, and a passing verifier.
Take agentlas-ai/agentlas-os-openclaw-hephaestus-network from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.