Real Skill packageSource verifiedClawHub registry

harness

This skill should be used for multi-session autonomous agent work requiring progress checkpointing, failure recovery, and task dependency management. Triggers on '/harness' command, or when a task involves many subtasks needing progress persistence, sleep/resume cycles across context windows, recovery from mid-task failures with partial state, or distributed work across multiple agent sessions. Synthesized from Anthropic and OpenAI engineering practices for long-running agents.

Identity and source

Publisher attributioneohmigregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 60% rule confidence
Package forminstruction with code13 recorded files
Canonical sourceClawHub registryclawhub:eohmig:harness
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 · 9/20/2026.claude/skills/harness

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 · 9/20/2026.agents/skills/harness

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 · 9/20/2026skills/harness

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 @eohmig/harness
clawhub inspect @eohmig/harness --version 1.0.0

Security evidence

SkillVetAI static result: no findings detected

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
13 / 13 inspected as text
Checked
9/20/2026, 4:53:41 AM
Scanner
0.1.3
Policy
1.0.3
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
1 dependency and API indicators
  • api: clawhub.ai
External clawhub result: suspicious

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
9/19/2026, 8:23:20 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

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

Package content hashsha256:9745f5fcda42c60547c1b6429c3fd73811019d5b383ecf6e15ae673b754d21c4
Show up to 13 recorded paths
  • hooks/_harness_common.py
  • hooks/harness-claim.py
  • hooks/harness-renew.py
  • hooks/harness-sessionstart.py
  • hooks/harness-stop.py
  • hooks/harness-subagentstop.py
  • hooks/harness-teammateidle.py
  • hooks/hooks.json
  • hooks/self-reflect-stop.py
  • skill-card.md
  • SKILL.md
  • tests/e2e-100tasks.sh
  • tests/test_hooks.py

Source changelog

Big change: Harness v1.0.0 refactored for multi-session autonomous agent work with state persistence, robust concurrency, and standardized recovery. - Rewritten as a long-running agent framework for progress checkpointing, session recovery, and dependency-aware task management. - Dual progress files introduced: human-readable append-only log (harness-progress.txt) and structured state (harness-tasks.json). - Hooks system implemented for session events and task lifecycle with concurrency-safe file locking. - Previous topic markdowns, guardrails, and pipeline docs have been removed; replaced with single-system protocol documentation. - Skill now activates only when a .harness-active marker is present to guard against unintended execution. - Example commands and exhaustive configuration provided for initializing, running, monitoring, and extending agent sessions.