cursor-cloud-agents-when
Skill5 starsChanged 46 days agoMITView on GitHub
use this when choosing Cursor Cloud Agent or the local grok CLI for coding or heavy multi-step work — Cloud Agent for a remote repo or pull request, the grok CLI for work on this machine under build quota, and the operator's private SDLC repository for artifacts that live there. if Cursor credits are empty, degrade to the grok CLI. do not use on your own initiative, and do not implement with a bot token.
In this repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- maintainers/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- buying-researcherSkill
- debug-anthropicSkill
- debug-pocockSkill
- debugSkill
- discover-the-ideaSkill
- docs-google-styleSkill
- golang-safetySkill
- golang-securitySkill
- golang-testingSkill
- grok-acpSkill
- host-config-pyinfraSkill
- lang-cppSkill
- lang-csharpSkill
- lang-cSkill
- lang-dartSkill
- lang-dockerSkill
- lang-goSkill
- lang-javaSkill
- lang-js-tsSkill
- lang-kotlinSkill
- lang-luaSkill
- lang-makefileSkill
- lang-phpSkill
- lang-powershellSkill
- lang-protobufSkill
- lang-pythonSkill
- lang-rubySkill
- lang-rustSkill
- lang-shellSkill
- lang-sqlSkill
- lang-swiftSkill
- lang-terraformSkill
- language-routerSkill
- lang-web-markupSkill
- modern-pythonSkill
- pr-reviewSkill
- sdlc-artifactsSkill
- sdlc-onboardingSkill
- security-hardeningSkill
- shell-safetySkill
- tddSkill
- tracker-sdlcSkill
- ui-craftSkill
- ux-designSkill
- verify-before-doneSkill
- yagniSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 14 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈14
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 38
Keep product GitHub repositories separate from the operator's private SDLC repository.
- Distinctive: line 43
Use Cursor Cloud Agent when any of these holds:
- Distinctive: line 53
If a requested Cloud Agent run fails on usage, credits, quota, or billing, that request also approves the grok CLI for the same goal.
- Distinctive: line 57
If Cloud Agent fails because of usage, credits, quota, or billing:
- Distinctive: line 61
If a remote pull request was required, produce the patch on this machine.
- Distinctive: line 63
If step 3 applies, open or hand off the pull request from an approved host that already has credentials, or give the operator a …
- Distinctive: line 66
If the grok CLI is also unavailable, stop and report both blockers.
- Distinctive: line 68
Do not retry in a tight loop.
- Distinctive: line 69
Do not implement with a bot token, including for a large patch.
- Distinctive: line 71
Do not work around the block with cookies or a Windows host.
- Distinctive: line 76
If the repository is ambiguous, confirm it with the operator.
- Distinctive: line 80
Do not poll. Wait for the run to complete, then resume.
- Distinctive: line 81
Follow up with a reply.
- Distinctive: line 83
Keep bank, mail, password-store, VPN, and chat secrets out of the prompt.
≈ “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
Cloud Agent vs grok CLI
Choose the worker for coding or heavy multi-step work: Cursor Cloud Agent, the local grok CLI, or both.
Iron law
Builds go to the grok CLI, Cursor Cloud Agents, or both. Do not implement with a bot token; hand the build to one of those workers.
Hand-off
- Hand off the whole ticket.
- Let the worker own the implementation loop.
- verifier checks the final result.
How remote agents and local CLIs fit the process: Workers. A worker's pull request into this repo still goes through intake: Workers.
Default split
| Work | Use |
| Design, review, scratch work, or build-quota research on this machine | grok CLI |
| A change that must land as a remote branch or pull request | Cursor Cloud Agent |
| Greenfield work with no repository named | Cloud Agent new_repo |
| SDLC artifacts that live in the operator's private SDLC repository | That repository, often through a Cloud Agent pull request |
| Files that exist only on a host with no remote checkout | grok CLI or shell on that host |
| Windows, or any host outside the workspace | Off limits unless the operator approved that host: Never |
Keep product GitHub repositories separate from the operator's private SDLC repository.
Prefer Cloud Agent when
Use Cursor Cloud Agent when any of these holds:
- The deliverable is a branch or a pull request on a connected remote repository.
- The deliverable lands in the operator's private SDLC repository, connected as a remote repository.
- The work needs Cursor source control or a cloud VM.
Credit degrade
If a requested Cloud Agent run fails on usage, credits, quota, or billing, that request also approves the grok CLI for the same goal. Fall back without a new ask.
If Cloud Agent fails because of usage, credits, quota, or billing:
- Say once that Cloud Agent failed on usage, credits, quota, or billing.
- Fall back to the grok CLI for the same goal.
- If a remote pull request was required, produce the patch on this machine.
- If step 3 applies, open or hand off the pull request from an approved host that already has credentials, or give the operator a branch-ready diff.
- If the grok CLI is also unavailable, stop and report both blockers.
- Do not retry in a tight loop. Fall back as above.
- Do not implement with a bot token, including for a large patch. Use the grok CLI or a branch-ready diff.
- Do not work around the block with cookies or a Windows host. Stop and report the blocker.
Launch
- If the repository is ambiguous, confirm it with the operator.
- Launch with a clear goal, the constraints, and what done looks like.
- On launch and on reply, prefer Grok 4.7 unless the operator names another model.
- Do not poll. Wait for the run to complete, then resume.
- Follow up with a reply.
- Interrupt a run only when asked.
- Keep bank, mail, password-store, VPN, and chat secrets out of the prompt.
For the grok CLI, the run steps are in grok-acp.
Load it when the operator opts in to Grok Build over ACP, or when Credit
degrade falls back to the grok CLI.
Roles
Role names and jobs: Roles. Tracker writes: Tracker. Host lock: Never.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

