operator-heartbeat
Skill0 starsChanged 4 months agoMITView on GitHub
Use to refresh local awareness, determine what changed, and select the next safe action without external execution.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- context-hydrationSkill
- project-bootstrapSkill
- safe-operatorSkill
- session-continuitySkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Read state/reports/OPERATOR_HEARTBEAT_latest.md and JSON evidence.
- Distinctive: line 11
Create local drafts only; never send, publish, authenticate, deploy, or schedule without exact approval.
- Distinctive: line 12
Avoid repeating an already surfaced item unless evidence changed.
- Distinctive: line 13
Update the session state and checkpoint Focusa after meaningful verified progress.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Operator Heartbeat
- Run
python3 scripts/operator_heartbeat.py. - Read
state/reports/OPERATOR_HEARTBEAT_latest.mdand JSON evidence. - Identify missing context, changed runtime state, active goal, and one highest-value next action.
- Create local drafts only; never send, publish, authenticate, deploy, or schedule without exact approval.
- Avoid repeating an already surfaced item unless evidence changed.
- Update the session state and checkpoint Focusa after meaningful verified progress.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

