Skip to content
Agent Orchestration
Skill

/hephaestus-storm

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

From plugin
agentlas-os
1.5k47 skills6 agents45 commands2 MCP

Claude Code

$ npx -y skills add agentlas-ai/Agentlas-OS --skill hephaestus-storm --agent claude-code

SKILL.md

hephaestus-storm.SKILL.md
name: hephaestus-storm
description: "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."

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

Hephaestus Stormbreaker Loop

Drive a goal through the **Stormbreaker Loop** — Hephaestus' force-robust, verifier-first execution loop. Unlike a one-shot answer or a generic parallel fan-out, Stormbreaker **routes the goal to real Agentlas specialists**, structures the work as a dependency-ordered pipeline fabric, drives each work packet as a **hardened goal loop** (it does not stall, run away, or claim false success), and **refuses to report success without evidence**. Never guess an agent yourself when this skill is active — the router or Hub decides the workforce.

Core-owned Goal + UltraCode harness

Every `hep-storm` result includes `execution_harness`. Before planning or executing any packet, apply `execution_harness.system_prompt` **verbatim** and retain its `prompt_sha256` in the goal ledger. This adapter must never redefine, summarize, or replace Goal mode or UltraCode mode with host-local wording. The adapter owns invocation only; Agentlas Core owns the execution protocol.

If the host exposes live Codex, Claude Code, Antigravity, local-model, or other sessions, provide their JSON array through `AGENTLAS_SESSION_INVENTORY` or `--session-inventory`. If it does not, accept Core's explicit `host:primary` fallback; never invent a model ID or claim unavailable parallel workers.

With no external executor, the runner intentionally returns `status: materialized` and `final_gate.can_report_success: false`. That is the host's signal to execute the returned packets with its native tools; it is not a failure and must never be rewritten as completion.

1. Resolve the runner

Run this resolution in a shell and use the first hit:

RUNNER=""
for c in \
  "$HOME/.agentlas/runtime/current/bin/hephaestus" \
  ./bin/hephaestus
do [ -x "$c" ] && RUNNER="$c" && break; done
if [ -z "$RUNNER" ]; then
  for cache in \
    "$HOME/.claude/plugins/cache/agentlas-core-engine/hephaestus" \
    "$HOME/.codex/plugins/cache/agentlas-core-engine/hephaestus"; do
    newest="$(ls -d "$cache"/*/bin/hephaestus 2>/dev/null | sort -V | tail -1)"
    [ -n "$newest" ] && [ -x "$newest" ] && RUNNER="$newest" && break
  done
fi

If no runner exists, tell the user to run the one-touch installer: `curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Agentlas-OS/main/scripts/install-all-runtimes.sh | bash`

1.5 Core project first-contact contract

Every `hep-storm` call is a trusted plugin contact. Before routing or materializing packets, Agentlas Core synchronously creates or repairs the canonical private project soul memory, code map, ontology runtime, CareerGraph, and merge-only `.gitignore` block for all of `.agentlas/`. A blocked bootstrap receipt blocks the storm. The adapter must not substitute host-local files or a second bootstrap implementation.

2. Agentlas sign-in

Before routing, ensure Agentlas is signed in:

if [ "${HEPHAESTUS_AUTH_AUTOPOPUP:-1}" != "0" ]; then
  "$RUNNER" auth ensure >/dev/null 2>&1 || true
fi

This opens the user's default browser only when there is no valid local Agentlas sign-in yet. If a saved sign-in already exists, it silently reuses it. For CI/headless checks only, set `HEPHAESTUS_AUTH_AUTOPOPUP=0` and skip this step.

3. Route and materialize the execution fabric

The Stormbreaker engine routes the goal and materializes a pipeline fabric (packets, parallel groups, dependency gates, goal loops, a final gate, and a resumable journal). In an agentic runtime **you are the executor** — the engine gives you the verified plan; you carry it out with your own tools. No `--executor-command`: the host model (you) executes each packet natively. `--research-evidence` grounds plan/research packets with Research Engine receipts.

FABRIC="$("$RUNNER" hep-storm "<the user's goal>" --research-evidence --runtime "${AGENTLAS_HOST_RUNTIME:-agent-skills}")"
printf '%s\n' "$FABRIC"

4. Branch on the route decision

Read `route_decision.action` (or `route_action`) and branch — Stormbreaker only auto-materializes a full fabric for a **pipeline**; other actions still start a storm, just with the workforce the router chose:

  • **`pipeline`** — the result carries the `execution_fabric` (`packets`,

`parallel_groups`, `sessions`, `resume_policy`), per-packet `write_scope` and `goal`/verifier, a `pipeline_id`, a `journal` path, and `final_gate` criteria. Run the full loop in §5.

  • **`clarify`** — the goal is ambiguous. Ask `clarify_question` with the candidate

list as ONE batch, then re-run `"$RUNNER" hep-storm "<refined goal>"`. This is the scope-lock ambiguity gate; do not guess past it.

  • **`route`** (single card) — a one-agent storm: borrow and run that card attached

to this project, then still apply the verify → repair → final-gate steps.

  • **`hub_fallback` / `hub_candidates`** — Hub lookup used redacted keywords only.

If an `execution` block lists `recommended_agents`, borrow each in stage order via `"$RUNNER" hep-call "<agent>" "<goal>" --project .` and run them attached to this repo; otherwise report candidates and offer `/hep-build`.

  • **`propose_new`** — no fit exists; offer to build one via `/hep-build`.
  • **`refuse`** — explain `reasons` (e.g. loop guard) and stop. Do not retry around

it.

5. Run the Stormbreaker Loo

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 skills on agentlas-os.

agentlas-operations

agentlas-operations

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

More skills from other plugins.

1password

1password

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

clawdis12d393k
@steipete@steipeteInstall Skill
computer-use

computer-use

Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and…

orca12d111k
@stablyai@stablyaiInstall Skill
agentmail

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…

paperclip12d109k
@paperclipai@paperclipaiInstall Skill
adr-create

adr-create

Create a new Architecture Decision Record with sequential numbering and AgentDB registration

@ruvnet@ruvnetInstall Skill

Questions about hephaestus-storm.

Which coding agents can use hephaestus-storm?
hephaestus-storm installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.