ClawHub

Background Delivery SOP

v1.2.0

Standardize how agents handle tasks that run in the background, via sub-agents, or via ACP sessions, so completed work is always proactively delivered back t...

⭐ 0· 45·0 current·0 all-time
by@wangwang0301
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name and description match the actual content: an SOP about how agents should acknowledge and deliver background work. The skill requests no binaries, env vars, or installs, which is appropriate for a pure policy/instruction document.
✓
Instruction Scope
SKILL.md contains prescriptive messaging rules for start acknowledgments, completion delivery, and classification of completion states. It does not instruct the agent to read unrelated files, access credentials, call external endpoints, or perform actions outside orchestration and user-facing messaging.
✓
Install Mechanism
No install spec or code files are present; this is instruction-only, so there is no disk installation or third-party package risk.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. That matches the SOP nature and is proportionate to the described functionality.
ℹ
Persistence & Privilege
always is false (normal) and model invocation is allowed (the platform default). Autonomous invocation plus a delivery SOP increases the agent's ability to proactively notify users — expected here but worth noting if you want to limit autonomous messaging.
Assessment
This instruction-only SOP is coherent and low-risk: it merely prescribes how agents should acknowledge and deliver results for background work. Before installing, consider whether you want agents to proactively send messages (autonomous invocation is allowed by default); if you prefer stricter control, disable autonomous invocation or test the SOP in a limited environment. Also confirm organizational policies about automatic user notifications and handling of potentially sensitive output (the SOP advises summarizing rather than dumping raw internal logs, which is good practice). Overall, no technical red flags were found.

Like a lobster shell, security has layers — review code before you run it.

latestvk975wmr2xaek43pm4704kn930h847vz1

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments