primeintellect-ai/prime-agent

rlm-heartbeat

Manage agent-owned RLM heartbeats from the Python REPL.

Quelltext ansehen

Verwendung

  1. Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
  2. Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
  3. Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/primeintellect-ai/prime-agent --skill rlm-heartbeat

Vor dem Start

  • Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
  • Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Originales Skill-Dokument

Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.

RLM Heartbeat

RLM heartbeats are internal recurring prompts for the current agent session. They are separate from the user's visible /heartbeat: this skill cannot read, replace, pause, resume, or clear that user-level heartbeat.

Call directly from the Python REPL:

python
await rlm_heartbeat.create("check test progress", interval="5m", label="tests")
await rlm_heartbeat.create("watch build", delivery_mode="follow_up")
await rlm_heartbeat.list()
await rlm_heartbeat.update("job-id", status="pause")
await rlm_heartbeat.delete("job-id")

API

  • await rlm_heartbeat.list(include_inactive=False) — list this session's

internal RLM heartbeats. By default this includes active and paused entries.

  • `await rlm_heartbeat.create(instruction, interval=None, label=None,

deliverymode=None)` — create a recurring heartbeat for this session. The default interval is every 5 minutes. Multiple RLM heartbeats may run at once; use labels to distinguish them. `deliverymode is "steer" (default) or "follow_up"`.

  • `await rlm_heartbeat.update(id, instruction=None, interval=None, label=None,

status=None, deliverymode=None)` — update one RLM heartbeat by id. `status` may be `"pause"` or `"resume"`; `deliverymode may be "steer" or "follow_up"`.

  • await rlm_heartbeat.delete(id) — cancel one RLM heartbeat by id.

Delivery mode

Each heartbeat has a delivery mode controlling how the scheduled prompt reaches the session when it is busy:

  • steer (default): interrupt the current turn so the heartbeat runs promptly.
  • follow_up: wait for the current turn to finish before running the heartbeat.

Rules

  • Use this when the user asks you to start, create, schedule, or manage your own

heartbeat without explicitly referring to /heartbeat.

  • Use this only for agent-internal recurring checks and long-running task

coordination.

  • Do not use this skill to satisfy a user's request to configure /heartbeat;

that is a separate user-level surface.

  • Keep heartbeat instructions specific and actionable so each recurring turn

knows exactly what to inspect or continue.

Verwandte Aufgaben

aus demselben Repository

Weitere Skills

Alle Skills