agentlas-core-engine-m…
Use when creating a single Agentlas agent, creating a multi-agent team, or packaging an existing local/external agent into…
Prepare explicitly named Agentlas Hub or Cloud agents.
Claude Code
$ npx -y skills add agentlas-ai/Agentlas-OS --skill hep-call --agent claude-code
Codex
$ npx skills add agentlas-ai/Agentlas-OS --skill hep-call -a codex -y
Cursor
$ npx skills add agentlas-ai/Agentlas-OS --skill hep-call -a cursor -y
Gemini CLI
$ npx skills add agentlas-ai/Agentlas-OS --skill hep-call -a gemini-cli -y
GitHub Copilot
$ npx skills add agentlas-ai/Agentlas-OS --skill hep-call -a github-copilot -y
OpenCode
$ npx skills add agentlas-ai/Agentlas-OS --skill hep-call -a opencode -y
Windsurf
$ npx skills add agentlas-ai/Agentlas-OS --skill hep-call -a windsurf -y
name: hep-call description: Prepare explicitly named Agentlas Hub or Cloud agents.
Update fallback: 자동 업데이트가 안 되면 `hephaestus update`를 한 번 실행하세요. 업데이트하지 않아도 현재 버전 명령은 그대로 동작합니다.
Call the exact agents named by the user. This prepares BYOM runtime bundles and receipts; your own model still performs the actual model/tool execution.
Syntax: `/hep-call agent-a, agent-b {context}`. The text before `{` is the agent list; the text inside braces is the context. If braces are omitted, the first token is the agent list and the rest is context.
Public Hub agent calls are free. Explain that scheduled work still uses the host's own model, API keys, permissions, and runtime capacity. Do not quote or purchase a retired Hub lease.
Run the shell block below **verbatim**, replacing only the `RAW` value with the exact text the user typed after `/hep-call`. The runner is resolved by **absolute path** — nothing to install, nothing to add to `PATH`.
> Guardrails: do NOT diagnose `command not found`/`PATH`, do NOT edit > `~/.zshrc`, and do NOT create/commit/stash/push any git branch or claim you > did. This workflow changes no source files. If the runner is missing, say so > and stop — never fabricate a run.
RAW="<replace with the exact text the user typed after /hep-call, e.g. agent-a, agent-b {context}>"
case "$RAW" in
"<replace"*) echo "RAW placeholder not filled — substitute the user's request first." >&2; exit 2 ;;
esac
RUNNER=""
for candidate in \
"$HOME/.agentlas/runtime/current/bin/hephaestus" \
"./bin/hephaestus"
do
if [ -n "$candidate" ] && [ -x "$candidate" ]; then RUNNER="$candidate"; break; fi
done
if [ -z "$RUNNER" ]; then
for cache in "$HOME/.claude/plugins/cache/agentlas-core-engine/hephaestus" \
"${CODEX_HOME:-$HOME/.codex}/plugins/cache/agentlas-core-engine/hephaestus"; do
newest="$(ls -d "$cache"/*/bin/hephaestus 2>/dev/null | sort -V | tail -1)"
if [ -n "$newest" ] && [ -x "$newest" ]; then RUNNER="$newest"; break; fi
done
fi
[ -n "$RUNNER" ] || { echo "Hephaestus runtime not found. Run the installer first." >&2; exit 1; }
if [ "${HEPHAESTUS_AUTH_AUTOPOPUP:-1}" != "0" ]; then
"$RUNNER" auth ensure >/dev/null 2>&1 || true
fi
if printf '%s' "$RAW" | grep -q '{'; then
AGENTS="${RAW%%\{*}"
CONTEXT="${RAW#*\{}"
CONTEXT="${CONTEXT%\}}"
else
AGENTS="${RAW%% *}"
CONTEXT="${RAW#* }"
fi
AGENTS="$(printf '%s' "$AGENTS" | sed 's/[[:space:]]*$//')"
CONTEXT="$(printf '%s' "$CONTEXT" | sed 's/^[[:space:]]*//;s/[[:space:]]*$//')"
"$RUNNER" call "$AGENTS" "$CONTEXT" --runtime "${AGENTLAS_HOST_RUNTIME:-terminal}"1. Report each requested agent slug and status. 2. If `status: "prepared"`, use the returned `output.entry_excerpt` and `output.grounding.directive` as the agent's runtime instructions. 3. If a legacy server returns `status: "insufficient_credits"`, do not run the agent or suggest a top-up. Report that the server has not switched to the free Hub contract. 4. If an agent fails for any other reason, continue with prepared agents and clearly list each failure with its `status`. 5. NEVER substitute for a blocked or failed agent by reading its local source files and role-playing the persona yourself. A Hub agent runs only through the server's pinned bundle; if it did not return `prepared`, report why — never fabricate a run. 6. Include the top-level `receipt_id` and every prepared `execution_id`.
/hep-call market-researcher, report-writer {시장 리포트 초안 만들어줘}
/hep-call cloud:my-finance-agent {이 리포트 리스크 검토}---
Update fallback: 자동 업데이트가 안 되면 `hephaestus update`를 한 번 실행하세요. 업데이트하지 않아도 현재 버전 명령은 그대로 동작합니다.
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.
Use when creating a single Agentlas agent, creating a multi-agent team, or packaging an existing local/external agent into…
Use when converting, repairing, or packaging an existing local or external agent/team into Agentlas architecture for local…
Use when generating a single installable agent that should keep learning, track sources, refresh research, propose repairs, or…
Turn the current interactive conversation into an owner-reviewed reusable Agentlas agent; accept JSON or JSONL only for explicit…
Use when generating or auditing a multi-role agent team package with orchestrator, PM Soul, Memory Curator, Policy Gate, workers,…
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…
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration