Agent Pulse
v0.1.0Standardized agent interruptibility and load-status check with fixed trigger words and fixed output. Use when the user sends `Agent Pulse` or `/pulse`, asks...
⭐ 0· 103·0 current·0 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 (lightweight interruptibility pulse) align with included scripts and triggers. The skill does not request unrelated credentials, binaries, or config paths. It includes only two small local scripts that evaluate signals and render a fixed card.
Instruction Scope
SKILL.md limits inputs to cheap signals and requires a fixed five-line card; the provided scripts implement the rule set and the renderer. One minor inconsistency: the SKILL.md and fixed output contract ask to 'Include current context usage ratio when available' (contextRatio), and the renderer prints contextRatio, but pulse_eval.py does not emit a contextRatio field. As a result the rendered card will show 'unknown' unless the caller supplies contextRatio in the signal JSON. Otherwise the instructions do not reference unrelated files, env vars, or external endpoints.
Install Mechanism
No install spec; this is instruction-only plus two small included scripts. No network downloads or external package installs are invoked by the skill itself.
Credentials
No environment variables, credentials, or config paths are required. The skill only consumes a JSON signal object (no secrets).
Persistence & Privilege
always:false and no requests to modify other skills or global agent settings. The skill does not demand persistent presence or elevated privileges.
Assessment
This skill appears coherent and low-risk: it only evaluates a supplied JSON of inexpensive signals and prints a fixed 5-line status card. Two practical notes before installing:
- The renderer prints a contextRatio field, but pulse_eval.py does not compute or include contextRatio; if you want that metric to appear, ensure whatever calls pulse_eval provides a contextRatio in the result or extend pulse_eval to calculate it.
- The skill will only be useful if the agent runtime is allowed to execute the included Python scripts; review runtime execution permissions if you run untrusted code in your agent environment.
If you want stricter guarantees, request the author add an explicit contextRatio calculation or document how callers should supply it.Like a lobster shell, security has layers — review code before you run it.
latestvk976j4cdmbsrgd7q2e8kt99ypn839d0n
License
MIT-0
Free to use, modify, and redistribute. No attribution required.