Restart Task Recovery
v1.0.0Preserve and resume in-progress multi-agent work across OpenClaw config patch/apply restarts. Use when a restart is required during active tasks, when users...
⭐ 0· 233·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description promise (preserve and resume multi-agent work across restarts) aligns with provided scripts and instructions: checkpoint building, parsing, verification, and generating send actions for sessions_send. No unrelated env vars, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs only local checkpoint creation (memory/restart-checkpoints), parsing, verifying, and sending resume messages via the platform tool names (sessions_list, sessions_history, sessions_send). It does not instruct reading unrelated system files or exporting data to external endpoints. The pre-resume verifier intentionally flags potentially non-idempotent messages for manual confirmation.
Install Mechanism
Instruction-only skill with no install spec. Provided scripts are small, local Python/Bash utilities that perform file I/O and JSON processing. No downloads or archive extraction are used.
Credentials
No environment variables, credentials, or config paths are required. Scripts do minimal local file and optional TMPDIR use. There are no requests for unrelated secrets or cloud credentials.
Persistence & Privilege
Skill is not always-enabled and allows model invocation (normal). It writes its own checkpoint files under memory/restart-checkpoints (expected for its purpose) and does not modify other skills or global agent settings.
Assessment
This skill appears coherent and is designed to be a safe helper for resuming interrupted agent sessions, but review these before installing:
- Confirm 'sessions_list', 'sessions_history', and 'sessions_send' are the legitimate platform tooling you expect — the scripts generate payloads that rely on those tools.
- Check that checkpoint files (memory/restart-checkpoints) do not contain sensitive secrets or PII you don't want persisted; control access and retention of that directory.
- The pre-resume verifier flags messages with words like 'retry', 'write', 'create', 'update', 'delete', 'payment', 'transfer' as high risk — verify that the manual confirmation workflow is enforced in your environment before auto-sending any held actions.
- Test in a staging environment to ensure resume messages are idempotent and that automated 'send' actions don't trigger unwanted external writes.
If you want greater assurance, run a code review of the scripts in your environment and validate that sessions_send calls behave safely under your policies.Like a lobster shell, security has layers — review code before you run it.
latestvk97dh3dg9fkxepf221gzhfrzbn82jqnz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.