heyeddi-local-first
Skill0 starsChanged 7 days agoMITView on GitHub
ALWAYS-ON local-first gate for every agent. Prepare Terraform and config locally. terraform plan is allowed and must be summarized as a warning. classify_command.py --check exits 1 on terraform apply and other live cloud mutations. Use on any infra, Terraform, gcloud, Firebase, Kubernetes, or Google account change.
- Sends data out
In this repository41 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/heyeddi-always-on.mdcCursor rule
- .cursor/rules/skill-authoring.mdcCursor rule
- aura-design-tokensSkill
- backend-type-bridgerSkill
- cli-interface-designSkill
- composable-patternsSkill
- dart-type-bridgerSkill
- design-handoff-flutterSkill
- design-system-generalizerSkill
- engineering-excellenceSkill
- fancy-ui-craftSkill
- flutter-engineeringSkill
- flutter-patternsSkill
- heyeddi-ci-configSkill
- heyeddi-ci-failsSkill
- heyeddi-ci-guideSkill
- heyeddi-ci-runnersSkill
- heyeddi-designSkill
- heyeddi-handoffSkill
- heyeddi-intakeSkill
- heyeddi-orchestratorSkill
- heyeddi-productSkill
- heyeddi-pr-respondSkill
- heyeddi-pr-reviewSkill
- heyeddi-setupSkill
- heyeddiSkill
- layout-morphSkill
- motion-physicsSkill
- no-duplicate-uiSkill
- pre-merge-gateSkill
- primevue-auraSkill
- primevue-openprops-architectSkill
- project-engineeringSkill
- quasar-foundationSkill
- taste-penpotSkill
- ux-flow-auditorSkill
- verify-buildSkill
- visual-auditorSkill
- visual-verificationSkill
- vue-design-systemSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Before any Terraform, OpenTofu, Pulumi, gcloud, GAM, Firebase, kubectl, Helm, aws, gsutil, bq, or Google API write, run:
- Very specific: line 36
Run the checker on the plan command.
- Very specific: line 38
Commit and review that diff.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Local first
Always on for every agent that loads HeyEddi skills (Cursor, Claude, Codex, Cloud Run, or any other host). Edit code and Terraform in the repo. Check the plan. Do not change live systems.
This is the same kind of gate as verify_setup --check. The script exits 1 on a live mutation. Do not run that command.
Hard gate
Before any Terraform, OpenTofu, Pulumi, gcloud, GAM, Firebase, kubectl, Helm, aws, gsutil, bq, or Google API write, run:
python .agents/skills/heyeddi-local-first/scripts/classify_command.py --check --command "<the exact command>"From this hub, the script path is skills/heyeddi-local-first/scripts/classify_command.py.
| Exit | Meaning |
0 and "action": "allow" | Run it. Reads and local config only. |
0 and "action": "plan" | Run it. Then warn the user with what the plan would create, change, or destroy. Stop. |
1 and "blocked": true | Do not run it. Edit the files instead. |
A plan command is terraform plan, tofu plan, pulumi preview, or ansible-playbook --check.
Process
- Change the Terraform, config, or app code in the working tree.
- Run the checker on the plan command. Exit 0 with
action: planmeans run the plan. - Warn the user. Quote the resource addresses the plan would add, change, or destroy.
- Commit and review that diff. Live apply stays in the project's deploy pipeline (Cloud Build
terraform-releasefor HeyEddi CI) or in a terminal the human runs.
What exits 1
terraform/tofuapply,destroy,import,refresh,state rm,workspace deletegcloudwrites (delete,deploy,create,submit, IAM changes).list,describe,get,config, andauthstay allowed.- GAM writes, including calendar account changes.
gam infoandgam printstay allowed. firebase deploy, kubectl writes,helm upgrade, aws writes,gsutil rm,bqqueries that are not--dry_runcurl -X POST, PUT, PATCH, or DELETE to a Google API- The same commands inside
bash -c,python -c,$(...), or a local.sh/.pyscript
firebase emulators:start is local and stays allowed.
Tools
| Script | Purpose |
classify_command.py --check | Exit 1 on a live mutation. Plan prints a warning and exits 0. |
Related
@heyeddialways-on list@engineering-excellencefor the code change gate- HeyEddi CI
cloudbuild.yamlstepterraform-releaseis the reviewed apply path
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.

