Install
$ agentstack add skill-jesse-merhi-skills-openclaw-local-test ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
OpenClaw Local Test
Provide a ready-to-use local OpenClaw instance for manual testing in a browser.
Workflow
- Ensure the helper exists on
PATH.
Prefer ~/.local/bin/openclaw-local-test if present. If missing or clearly stale, install the bundled helper:
``bash install -m 755 scripts/openclaw-local-test ~/.local/bin/openclaw-local-test ``
- Start the full manual-test instance.
Pass the source config explicitly so the user can confirm which local credentials/config will be mirrored:
``bash openclaw-local-test --repo ~/repos/openclaw --base-config ~/.openclaw/openclaw.json ``
Read [references/options.md](references/options.md) for alternate repo, browser, lease, status, stop, and smoke-test options.
- Inspect the generated config before testing behavior.
The running Gateway uses ~/.openclaw-local-test/openclaw.json, not the source config directly. Read [references/config-inspection.md](references/config-inspection.md) for the redacted inspection command and reporting rules.
- Verify both endpoints after startup:
``bash curl -fsS http://127.0.0.1:/healthz curl -fsS http://localhost:/healthz ``
- Check logs when channel/provider readiness matters:
``bash tail -80 ~/.openclaw-local-test/logs/gateway.log tail -80 ~/.openclaw-local-test/logs/gateway.err.log ``
- Report only useful test details:
- browser URL, usually
http://localhost:/ - Gateway port and browser proxy port
- provider/model, usually
atlassian-aigw/gpt-5.5-2026-04-23 - config path, active agent id, and relevant permission/tool/plugin settings
- lease expiry time
- whether Slack and Discord started or any degraded logs appeared
openclaw-local-test --statusandopenclaw-local-test --stop
Context Pointers
- Read [references/helper-behavior.md](references/helper-behavior.md) when you
need to explain state paths, session rotation, model/config rewriting, proxy behavior, startup locks, TTL, or security posture.
- Read [references/troubleshooting.md](references/troubleshooting.md) when
startup, proxy, provider, channel, or cleanup behavior fails.
Done Means
- The helper path is installed or already present.
- The instance started from the intended OpenClaw repo and explicit base config.
- Health checks passed for both Gateway and browser proxy.
- The active generated config was inspected with secrets redacted.
- The report includes URL, ports, provider/model, relevant config summary, lease
expiry, channel status, and stop/status commands.
- Raw config, secrets, and credentials were not pasted into chat.
Avoid
- exposing the local Gateway/browser proxy publicly;
- interpreting behavior against the source config instead of the generated
runtime config;
- manually choosing ports while another startup is waiting on the lock;
- keeping reduced smoke-test instances running unless the user explicitly asks;
- using
openclaw-dia-testfor new instructions except as a compatibility
stop/status fallback.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jesse-merhi
- Source: jesse-merhi/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.