workspace-quality-gate
Skill2 starsChanged 56 days agoMITView on GitHub
Run non-destructive release-readiness checks for Codex Workspace and Workspace Hub
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- agent-tooling-doctorSkill
- quality-gateSkill
- repo-onboardingSkill
- runtime-triageSkill
- security-checkSkill
- ssh-keychain-accessSkill
- typescript-reviewSkill
- workspace-maintenanceSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when the task is about stable release checks, release readiness, or verifying that Codex Workspace changes did not regress …
- Very specific: line 14
If agent-tooling files changed, also run tools/scripts/doctor-agent-tooling.sh.
- Very specific: line 15
If shared skills or templates changed, dry-run tools/scripts/sync-codex-skills.sh repos/workspace-hub.
- Very specific: line 20
Do not mutate sibling repos under repos/ unless the user explicitly asks.
- Distinctive: line 21
Prefer temp fixtures and dry runs over editing existing repo content during verification.
- Distinctive: line 28
no placeholder TODO metadata remains in shipped workspace surfaces
≈ “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
Workspace Quality Gate
Use this skill when the task is about stable release checks, release readiness, or verifying that Codex Workspace changes did not regress the base environment.
Default checks
- Run
tools/scripts/release-readiness.sh. - If agent-tooling files changed, also run
tools/scripts/doctor-agent-tooling.sh. - If shared skills or templates changed, dry-run
tools/scripts/sync-codex-skills.sh repos/workspace-hub. - Confirm Workspace Hub tests, lint, and build pass before calling the change release-ready.
Safety rules
- Do not mutate sibling repos under
repos/unless the user explicitly asks. - Prefer temp fixtures and dry runs over editing existing repo content during verification.
- Preserve existing repo files when testing agent preset scaffolding.
Expected release signals
doctor-workspace.shreports the workspace as readyworkspace-hubpassespnpm test,pnpm lint, andpnpm build- no placeholder TODO metadata remains in shipped workspace surfaces
- the documented
.codex/contract matches the implementation
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.

