Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

runner-liveness-guardrails

Sterne0

Forks0

Aktualisiert18. Februar 2026 um 07:00

Preserve 24/7 local runner operation and control-target accuracy during upgrades. Use when changing runner start/stop, launcher APIs, runner credential issuance, port detection, or multi-instance behavior.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

tokamak-network

tokamak-network/24-7-playground

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

Netzwerk- und ComputersystemadministratorenInformatik- und Mathematikberufe·SOC 15-1244

SKILL.md

readonly

name	runner-liveness-guardrails
description	Preserve 24/7 local runner operation and control-target accuracy during upgrades. Use when changing runner start/stop, launcher APIs, runner credential issuance, port detection, or multi-instance behavior.

Runner Liveness Guardrails

Preserve runtime independence

Keep runner alive without active owner browser session.
Keep long-lived runtime auth scoped to runner credential, not web session bearer.

Enforce control-target accuracy

Treat runner as running for a selected agent only if launcher status matches selected agentId.
Before start, preflight selected port and block if occupied by another agent.
Before stop, preflight selected port and block stop for agent mismatch.
Preserve explicit user-selected port; do not force-switch silently.

Preserve observability

Keep per-port log separation and metadata stamping (instanceId/port/pid/agentId).
Keep communication/full-trace logging behavior intact when touching engine boundaries.
Keep runner<->agent communication semantics (action schema + tx_feedback logging) stable; pair with runner-communication-protocol-guardrails when changing protocol fields.

Required scenario checks

Execute 2-port/2-agent matrix (4391/4392, agents A/B).
Verify cross-select start/stop mismatch blocking.
Verify log files remain separated by port and stamped with instance metadata.

Mehr aus diesem Repository

gleiches Repository

auth-and-permission-guardrails

tokamak-network/24-7-playground

Guard authentication, authorization, and action-permission correctness in SNS workflows. Use when changing login/session flows, nonce/signature validation, owner-agent permission boundaries, or thread/request/report state transitions.

2026-03-020

upgrade-scope-triage

tokamak-network/24-7-playground

Triage and route any non-trivial upgrade request in this repository by risk, impacted boundaries, and required guardrail skills. Use when a task touches auth, runner runtime, API contracts, schema, permissions, or docs.

2026-03-010

docs-and-handover-guardrails

tokamak-network/24-7-playground

Keep operator and handover documentation aligned with behavior changes. Use when upgrades alter auth flow, runner operations, API behavior, permissions, schema assumptions, or UX workflows documented in project guides.

2026-02-240

runner-communication-protocol-guardrails

tokamak-network/24-7-playground

Define and protect protocol contracts between Runner and the LLM agent, and between Runner and SNS APIs. Use when changing runner prompts, decision/action schema, communication logs, SNS client routes, auth headers, nonce-signature logic, or request-status/tx feedback semantics.

2026-02-240

security-boundary-guardrails

tokamak-network/24-7-playground

Enforce non-negotiable security boundaries for SNS and Runner upgrades. Use when code changes can affect secrets, auth/signing, launcher access, CORS, network flows, logging redaction, or credential storage.

2026-02-240

deploy-build-guardrails

tokamak-network/24-7-playground

Prevent deploy/build failures for SNS and Runner by enforcing guardrails around Next.js render mode, Prisma/DB access timing, environment wiring, and pre-merge verification. Use when changing build scripts, route segment config (`dynamic`/`revalidate`), Prisma usage, or Vercel deployment settings.

2026-02-230

name	runner-liveness-guardrails
description	Preserve 24/7 local runner operation and control-target accuracy during upgrades. Use when changing runner start/stop, launcher APIs, runner credential issuance, port detection, or multi-instance behavior.

Runner Liveness Guardrails

Preserve runtime independence

Keep runner alive without active owner browser session.
Keep long-lived runtime auth scoped to runner credential, not web session bearer.

Enforce control-target accuracy

Treat runner as running for a selected agent only if launcher status matches selected agentId.
Before start, preflight selected port and block if occupied by another agent.
Before stop, preflight selected port and block stop for agent mismatch.
Preserve explicit user-selected port; do not force-switch silently.

Preserve observability

Keep per-port log separation and metadata stamping (instanceId/port/pid/agentId).
Keep communication/full-trace logging behavior intact when touching engine boundaries.
Keep runner<->agent communication semantics (action schema + tx_feedback logging) stable; pair with runner-communication-protocol-guardrails when changing protocol fields.

Required scenario checks

Execute 2-port/2-agent matrix (4391/4392, agents A/B).
Verify cross-select start/stop mismatch blocking.
Verify log files remain separated by port and stamped with instance metadata.