agentcore-operations
Skill1 starsChanged 2 months agoMITView on GitHub
Review, release, troubleshoot or retire an AgentCore deployment using exact image/runtime identity, configuration ownership and scoped operational evidence. Use for deployment drift, stale secrets, readiness or cleanup; not for routine agent prompt development.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agentcore-gatewaySkill
- agentcore-runtimeSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Read configuration and release identity for stale settings and drift, or retirement and recovery for cleanup.
- Distinctive: line 27
Keep those evidence levels separate.
- Distinctive: line 32
Stop retrying unchanged infrastructure after a repeated failure at the same boundary.
- Distinctive: line 34
Do not export raw secrets, user data or invocation bodies into diagnostic artifacts.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Operate the version that is actually running
Establish deployment ownership and the requested operation first. Read-only review is not a request to redeploy; existing explicit deployment approval need not be requested again. Preserve the project's release and rollback process.
Read configuration and release identity for stale settings and drift, or retirement and recovery for cleanup.
Evidence to collect
- Source revision and isolated image-test result.
- Registry digest and deployed runtime version/endpoint binding.
- Configuration source and adoption time, without secret values.
- One check of the disputed live behavior, where authorized.
- Remaining uncertainty and the next observation that can resolve it.
Keep those evidence levels separate. A historical document, green source CI or a mutable image tag cannot independently establish the deployed behavior.
Inspect only what resolves the current question. Reuse unchanged valid checks; repeat a check when its inputs changed or a failure calls its result into question. Stop retrying unchanged infrastructure after a repeated failure at the same boundary.
Do not export raw secrets, user data or invocation bodies into diagnostic artifacts. Prepare exact changes before a mutation and retain rollback/recovery information appropriate to the operation.
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.

