agentlas-ai/hephaestus

Use when designing a new multi-agent team, visible agents folder, role boundaries, handoff flow, PM Soul, Memory Curator, Policy Gate, or evaluation role. Use for agent-team repo creation even when the user only says they want a meta-agent or agent operating system.

Single entry point for every Agentlas command: /agentlas network, /agentlas build, /agentlas storm, /agentlas graph, /agentlas one, /agentlas upload, /agentlas cloud, /agentlas hub, /agentlas local, /agentlas browser, /agentlas call, /agentlas search, /agentlas connect, /agentlas login, /agentlas orch, /agentlas update.

Use when adding or auditing local runtime behavior that turns a project folder into an Agentlas-aware workspace with .agentlas memory and sitemap files.

Use when the user types /agentlas-browser <url-or-query>, /agentlas browser, or /hep-browser for browser-required tasks, rendering pages, form flows, or visual evidence.

Use when the user types /agentlas-build, /agentlas build, or /hep-build to design, build, and package a single agent or multi-agent team.

Use when the user types /agentlas-call <agents> <context>, /agentlas call, or /hep-call to borrow and execute named Agentlas Hub/Cloud agents attached to the current project.

Use when the user types /agentlas-cloud, /agentlas cloud, or /hep-cloud to staff only from the signed-in owner's private Cloud packages.

Use when the user types /agentlas-connect <channel>, /agentlas connect, or /hep-connect to connect Agentlas channels (Slack, Discord, Telegram, etc.).

Use when the user types /agentlas-graph, /agentlas graph, or /hep-graph to create, list, inspect, or run Agentlas automation graphs.

Use when the user types /agentlas-hub, /agentlas hub, or /hep-hub to staff only from the public Agentlas Hub marketplace.

Use when the user types /agentlas-local, /agentlas local, or /hep-local to staff only from registered Local packages.

Use when the user types /agentlas-network, /agentlas network, $hephaestus-network, or /hep-network to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams.

Use when the user types /agentlas-one on|off, /agentlas one on|off, or asks to enable/disable the persistent personal agent mode.

Agentlas 시스템 운용 절차 — hep-network 편성, hep-graph 자동화, cargo/Agent Cloud·marketplace 활용, workforce 로스터 재사용, 메모리 계약. One(개인 에이전트)이 Agentlas를 조작할 때 이 절차를 따른다.

Use when converting, repairing, or packaging an existing local or external agent/team into Agentlas architecture for local install, Agentlas import, Codex plugin use, Claude adapter use, or open-source release.

Use when the user types /agentlas-search <query>, /agentlas search, or /hep-search to search across Local, Cloud, and Hub agent repositories.

Use when an agent folder must pass the Agentlas Cloud 2-stage security scan (static rules + BYOK LLM judgment) before private sync or public publish, or when asked to run/interpret hephaestus security scan.

Use when the user types /agentlas-storm, /agentlas storm, /hep-storm, or says @Hephaestus storm <goal> to drive a goal through the force-robust Stormbreaker loop with real Agentlas specialists.

Use when the user types /agentlas-upload, /agentlas upload, $hephaestus-upload, or /hep-upload to scan, gate, and publish an agent/team package to Agentlas Cloud (private) or Agentlas Hub (public).

Use when a meta-agent request is too ambiguous to safely generate, package, publish, or adapt without one to five targeted questions.

Use when the user types /hep-cloud or /agentlas-cloud, or asks to staff from THEIR OWN Agentlas cloud packages only. Cloud is one exact source scope; Network means Local + owner Cloud + public Hub.

Use when the user types /hep-graph or asks to create, list, inspect, or request a run of an Agentlas automation graph.

Use when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion.

Use when the user types /hep-storm or /agentlas-storm, says @Hephaestus storm <goal>, or asks to drive a goal to verified completion through a force-robust Stormbreaker loop. Stormbreaker routes the goal to real Agentlas specialists, materializes a dependency-ordered pipeline fabric, and runs each work packet as a verifier-first hardened loop that does not stall, run away, or claim false success. Use it for loop-worthy work — apps, sites, agents, automations, debugging, multi-step research, data/report generation. Trivial questions are answered directly, not stormed.

Use when the user types $hephaestus-upload, /hep-upload, or /agentlas-upload, or asks to upload, publish, or list an Agentlas agent or team. Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate.

Use before claiming that the package can be installed or published. Verifies structure, adapters, schemas, executable scripts, and public-safety boundaries.

Use when designing how one canonical agent core runs across Codex, Claude Code, Gemini CLI, Cursor, and AGENTS.md-compatible tools.

Use when adding Memory Events, Memory Tickets, memory-map.json, vault-references.json, PM Soul memory ownership, or Memory Curator routing to an agent repo.

Use before routing a /meta-agent request to choose single-agent-creator, team-builder, or agentlas-packager from the user's wording and available files.

Use when preserving product intent, acceptance criteria, decision memory, open loops, roadmap context, or the product-manager continuity layer of an agent team.

Use when packaging this meta-agent for public Codex plugin registration, Claude Code installation, GitHub release, one-line terminal install, or open-source distribution.

Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.

Use when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core. Use whenever a generated repo needs multiple AI runtimes without duplicating instructions.

Use when generating a single installable agent that should keep learning, track sources, refresh research, propose repairs, or improve itself over time without becoming a multi-agent team.

Turn the current interactive conversation into an owner-reviewed reusable Agentlas agent; accept JSON or JSONL only for explicit terminal and automation runs.

Use when creating or auditing an agent-team sitemap, Task Bias ledger, concept coverage, product surface map, validation chain, or missing-concept check.

Use when adding or auditing Agentlas skill lifecycle metadata, skill-registry.json, trial evidence, Curator promotion decisions, or first-class skill promotion gates.

Use when generating or auditing a multi-role agent team package with orchestrator, PM Soul, Memory Curator, Policy Gate, workers, eval, QA, handoffs, and runtime adapters.