OpenClaw Harness

Cross-session context manager for AI agents with checkpoint/snapshot, Build-Verify-Fix closure, and entropy management (GC). Use when: (1) creating a task ch...

This skill appears to implement the advertised checkpoint/verify/GC features, but there are important mismatches and risks you should consider before installing or running it: - Missing dependency/declarations: The code expects node, jq, openssl and other common utilities, but the skill metadata lists none. Verify/install those dependencies yourself or run the scripts in an environment where missing dependencies won't cause surprises. - Review and restrict verify rules: The 'harness verify' mechanism can execute arbitrary shell commands via 'command' rules. Never run verify with untrusted rules. Inspect any --rule JSON before use and prefer file/pattern checks over command checks unless you trust the commands. - Inspect memory-palace integration: The GC agent will try to call a 'memory-palace' node binary at an absolute path (/root/.openclaw/...). That may access workspace-level or root-owned data. If you don't run memory-palace, set ARCHIVE_PRIORITY=local or point MEMORY_PALACE_BIN to a trusted binary, or disable compression. - Run in isolation first: Test the skill in a throwaway container or dedicated VM and run gc with --dry-run initially. Do not enable daemon mode until you audit behavior. - Do not blindly install hooks: The docs mention pre-commit hooks that run harness verify and linter on commits — review those hooks before adding them; they could block commits or run commands during commits. - Ask the publisher for provenance: There is no homepage or clear source origin. If you need to use it in production, request a signed release, dependency list, and explicit explanation of why absolute paths are used and what memory-palace does. If you proceed, prefer changing defaults to local-only operations, disable daemon mode, run GC only with --dry-run first, and ensure the .harness root is inside the project directory (not /root) to avoid touching unrelated data.

Type: OpenClaw Skill Name: openclaw-harness Version: 1.0.3 The openclaw-harness skill bundle is a legitimate workspace and context management utility for AI agents, providing features for state snapshotting (checkpoints), task verification, and automated cleanup (GC). The bundle includes robust safety mechanisms such as a 'safe file' list in lib/harness-core.sh to prevent the deletion of critical identity and memory files, a trash system for archived deletions, and detailed logging in bin/gc-agent.sh. While the tool possesses high-risk capabilities like file deletion and command execution for verification, these are strictly aligned with its stated purpose and are implemented with appropriate safeguards and documentation.