Documents

ground-control

Try it

Verify OpenClaw after upgrades against an operator-maintained model, cron, and channel ground truth. Use for report-only config integrity, provider liveness, cron integrity, session smoke tests, and channel checks; require explicit approval before applying repairs.

What it does

Post-upgrade verification for OpenClaw. Keeps your system honest after every upgrade.

The skill document

ground-control

Post-upgrade verification for OpenClaw. Keeps your system honest after every upgrade.

🛠️ Installation

Tell OpenClaw: "Install the ground-control skill." Installation does not authorize runtime config or cron changes.

2. Manual Installation (CLI)

If you prefer the terminal, run:

openclaw skills install @jonathanjing/ground-control

Permissions & Privileges

This skill requires the following OpenClaw capabilities:

  • gateway config.get — read current config (all phases)
  • gateway config.patch — apply an operator-approved config repair (Phase 1 only)
  • cron list / cron update — verify cron jobs and apply operator-approved repairs (Phase 3)
  • sessions_spawn — smoke test sessions (Phase 2, 4, 5)
  • message send — channel liveness test + summary report (Phase 5)

Change-control behavior: Every run is report-only by default. Present a redacted repair plan and obtain explicit operator approval immediately before any gateway config.patch or cron update.

Security & Redaction: This skill enforces a Zero-Secret Logging protocol.

  • Immediate Redaction: Sensitive nodes (auth, plugins) are stripped from memory after fetching runtime config.
  • Redacted Drift: Mismatches in sensitive fields are reported as [REDACTED_SENSITIVE_MISMATCH].
  • Functional Validation: API keys are tested through functional calls (Phase 2), never through literal comparison.
  • No Persistence: Literal credentials are never written to memory/ files or messaging channels.

Environment variables: None.

When to use

  • After running openclaw update or npm install -g openclaw@latest
  • When you suspect config drift (model changed, cron broken, channel down)
  • Periodic health check via /verify command

Setup

  1. Copy {baseDir}/templates/MODEL_GROUND_TRUTH.md to your workspace root
  2. Fill in your actual config values (models, cron jobs, channels)
  3. (Optional) For large configs, split into refs/ground-truth/*.md sub-files
  4. Add the GROUND_TRUTH sync rule to your AGENTS.md (see README)
  5. Run /verify to test

Files

  • {baseDir}/templates/MODEL_GROUND_TRUTH.md — Ground truth template (copy to workspace root)
  • {baseDir}/scripts/post-upgrade-verify.md — Agent execution prompt for 5-phase verification
  • {baseDir}/scripts/UPGRADE_SOP.md — Upgrade standard operating procedure

Related skills

Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.

by Iván559 installs18 stars

Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.

by johnpatternai22 installs8 stars

Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.

by nssa.io1.0k installs47 stars

Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.

by Iván855 installs69 stars

Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.

by fly0pants4.3k installs296 stars

More from jonathanjing

Browse all skills

Operate and extend the read-only OpenClaw dashboard backend, frontend tabs, and security model.

by jonathanjing176 installs9 stars

Audit-grade SQLite ledger that records every model call's token usage and cost from OpenClaw sessions.

by jonathanjing28 installs

Monitor OpenClaw gateway health and report incidents to Discord with read-only checks and cooldown dedupe.

by jonathanjing41 installs

Multi-stage deep intelligence pipeline (Search → Filter → Fetch → Synthesize). Turns a query into a structured research report with full source citations.

by jonathanjing27 installs

Route user-selected photos from Meta Ray-Ban glasses or another camera through a configured messaging ingress to an approved specialist and destination. Use only for explicit, opt-in photo routing with allowlisted destinations and confirmation before cross-session forwarding or persistent writes.

by jonathanjing39 installs1 stars

Audit a named ClawHub skill or skill URL before installation by combining OpenClaw verification with bounded static analysis. Use when the user explicitly asks whether a skill is safe or requests a pre-install review; report evidence and uncertainty instead of treating a score as proof.

by jonathanjing39 installs