/hep-call
Prepare explicitly named Agentlas Hub or Cloud agents.
> /plugin marketplace add agentlas-ai/Agentlas-OS > /plugin install hephaestus@agentlas-core-engine
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/hep-call
Context preview
What this command does when you run it.
Prepare explicitly named Agentlas Hub or Cloud agents.
Command definition
hep-call.mddescription: Prepare explicitly named Agentlas Hub or Cloud agents.
argument-hint: 'agent-a, agent-b {context}'
allowed-tools: Bash, Read, Glob, GrepUpdate fallback: 자동 업데이트가 안 되면 `hephaestus update`를 한 번 실행하세요. 업데이트하지 않아도 현재 버전 명령은 그대로 동작합니다.
/hep-call
Call the exact agents named by the user. This prepares BYOM runtime bundles and receipts; Claude still performs the actual model/tool execution.
Raw arguments: `$ARGUMENTS`
Call
RUNNER=""
for candidate in \
"$HOME/.agentlas/runtime/current/bin/hephaestus" \
"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/bin/hephaestus}" \
"${PLUGIN_ROOT:+$PLUGIN_ROOT/bin/hephaestus}" \
"./bin/hephaestus"
do
if [ -n "$candidate" ] && [ -x "$candidate" ]; then RUNNER="$candidate"; break; fi
done
[ -n "$RUNNER" ] || { echo "Hephaestus runtime not found. Run the installer first." >&2; exit 1; }
if [ "${HEPHAESTUS_AUTH_AUTOPOPUP:-1}" != "0" ]; then
"$RUNNER" auth ensure --timeout 180 >/dev/null 2>&1 || true
fi
RAW="$ARGUMENTS"
if printf '%s' "$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 claude-codeAnswer Shape
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 `status: "insufficient_credits"`, tell the user the credits `needed` vs. `have` and point to `upgrade`; do NOT run the agent. Sign-in is automatic — if a call still reports an auth/sign-in status, relay it and stop. 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, failed, or metered agent by reading its local source files and role-playing the persona yourself. A Hub agent runs only through the server's metered bundle; if it did not return `prepared`, report why — never fabricate a run. 6. Include `receipt_id` and each prepared `execution_id`.
Examples
/hep-call market-researcher, report-writer {시장 리포트 초안 만들어줘}
/hep-call cloud:my-finance-agent {이 리포트 리스크 검토}Read more
description: Prepare explicitly named Agentlas Hub or Cloud agents.
argument-hint: 'agent-a, agent-b {context}'
allowed-tools: Bash, Read, Glob, GrepUpdate fallback: 자동 업데이트가 안 되면 `hephaestus update`를 한 번 실행하세요. 업데이트하지 않아도 현재 버전 명령은 그대로 동작합니다.
/hep-call
Call the exact agents named by the user. This prepares BYOM runtime bundles and receipts; Claude still performs the actual model/tool execution.
Raw arguments: `$ARGUMENTS`
Call
RUNNER=""
for candidate in \
"$HOME/.agentlas/runtime/current/bin/hephaestus" \
"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/bin/hephaestus}" \
"${PLUGIN_ROOT:+$PLUGIN_ROOT/bin/hephaestus}" \
"./bin/hephaestus"
do
if [ -n "$candidate" ] && [ -x "$candidate" ]; then RUNNER="$candidate"; break; fi
done
[ -n "$RUNNER" ] || { echo "Hephaestus runtime not found. Run the installer first." >&2; exit 1; }
if [ "${HEPHAESTUS_AUTH_AUTOPOPUP:-1}" != "0" ]; then
"$RUNNER" auth ensure --timeout 180 >/dev/null 2>&1 || true
fi
RAW="$ARGUMENTS"
if printf '%s' "$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 claude-codeAnswer Shape
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 `status: "insufficient_credits"`, tell the user the credits `needed` vs. `have` and point to `upgrade`; do NOT run the agent. Sign-in is automatic — if a call still reports an auth/sign-in status, relay it and stop. 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, failed, or metered agent by reading its local source files and role-playing the persona yourself. A Hub agent runs only through the server's metered bundle; if it did not return `prepared`, report why — never fabricate a run. 6. Include `receipt_id` and each prepared `execution_id`.
Examples
/hep-call market-researcher, report-writer {시장 리포트 초안 만들어줘}
/hep-call cloud:my-finance-agent {이 리포트 리스크 검토}Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
Other commands on agentlas-os.
- /agentlas
Agentlas commands — one entry point for network, build, storm, call, and the rest.
Open command - /hep-browser
Use the Agentlas browser hardpoint for browser-required work.
Open command - /hep-build
Build, repair, or package Agentlas agents and teams with Hephaestus.
Open command - /hep-cloud
Staff a task only from the signed-in owner's Agent Cloud agents.
Open command - /hep-connect
Connect Agentlas agents or teams to Telegram.
Open command - /hep-graph
Build an Agentlas automation by describing it, list saved ones, or request a run.
Open command

