Real Skill packageSource verifiedClawHub registry

claw-mechanic

Diagnose, audit, and repair OpenClaw hosts when an agent, gateway, plugin, cron, model route, memory engine, channel, approval policy, or update looks broken, expensive, slow, looping, stale, or misconfigured. Use for focused OpenClaw health checks, post-update triage, plugin update verification, model provider/API wiring audits, cron timeout/root-cause work, exec approval/reviewer problems, update admission refusals or half-failed updates, gateways stuck in restart or offline-maintenance loops, keychain-backed Se…

Identity and source

Publisher attributionB.K.registry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 67% rule confidence
Package forminstruction bundle6 recorded files
Canonical sourceClawHub registryclawhub:bkf-gitty:claw-mechanic
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 10/17/2026.claude/skills/claw-mechanic

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 10/17/2026.agents/skills/claw-mechanic

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 10/17/2026skills/claw-mechanic

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @bkf-gitty/claw-mechanic
clawhub inspect @bkf-gitty/claw-mechanic --version 1.1.0

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
6 / 6 inspected as text
Checked
10/17/2026, 4:22:39 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highInstructions or code access sensitive credential locationsSKILL.md:118 · confidence 85%keychain-backed SecretRefs need a one-shot GUI-domain LaunchAgent, not token extract
1 High/Critical review queue entry
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
Open human review queue →
3 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
2 dependency and API indicators
  • api: clawhub.ai
  • api: docs.openclaw.ai
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
10/16/2026, 11:53:37 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:98472f667e8a1bc9a6495c7ddb3d652fdc3b02ff56b326f175e4cd6c43d0756f
Show up to 6 recorded paths
  • _meta.json
  • references/failure-map.md
  • references/host-profile-template.md
  • references/root-failure-taxonomy.md
  • skill-card.md
  • SKILL.md

Source changelog

Adds update admission/rehearsal/recovery guidance (retired-state-format refusals, TMPDIR canary failures, half-migrated SQLite after a rolled-back update), macOS launchd/keychain traps (launchctl submit relaunch loops, one-shot GUI-domain jobs for keychain SecretRefs over SSH, Sparkle staged updates), and plugin pin/consent/provenance notes. Replaces the removed 'openclaw tasks' commands with 'status --all'/'audit', fixes log paths, and drops installs.json and plugins.bundledDiscovery.