Skip to content
Back to skills

Cases

ASecurity

- The current surface is ChatGPT Chat. - The user typed `/goal`. - The bundled plan skill is listed. - Native Plan mode is not observed active.

  • 6 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 20, 2026
ai-agentsgo

Security analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned September 27, 2026

npx -y skills add stark-ai-de/agent-skills --skill cases --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cases?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Cases
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/stark-ai-de-cases-4d17f9b2/badge)](https://www.skillsdirectory.com/skills/stark-ai-de-cases-4d17f9b2)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# ChatGPT Goal Command And Bundled Plan Skill Are Not Plan Mode

## Should Trigger

Yes.

## Runtime Context

- The current surface is ChatGPT Chat.
- The user typed `/goal`.
- The bundled plan skill is listed.
- Native Plan mode is not observed active.

## Prompt

Use Codex Spec Interviewer to define a safe migration from polling to webhook delivery. Interview me before producing the spec.

## Expected Behavior

- Continue permissible repository discovery and the material requirements conversation without requiring a manual Plan switch or complete UI enumeration.
- Keep planning capability and read-only enforcement separate; no interview mutations or writes while native Plan is active or state/permissions are unknown.
- Prepare the complete draft before a single positive checkpoint; retain unchanged approval across any required host exit.
- Keep unsupported or missing evidence indeterminate; do not infer a native control or technical absence. Resolve a capability question only when the next required action depends on it.
- Missing filesystem evidence remains indeterminate; do not probe enforcement with a write.

Files in this skill

  • agents-md-artifact-request.md821 B
  • already-specified-negative.md629 B
  • ambiguous-bug-report.md909 B
  • api-migration-plan.md860 B
  • architecture-change-needs-adr.md980 B
  • auth-permission-change.md718 B
  • batch-job-refactor.md683 B
  • chatgpt-plan-active-busy-composer.md1.1 KB
  • chatgpt-plan-active-enforcement-enforced.md908 B
  • chatgpt-plan-active-enforcement-unknown.md916 B
  • chatgpt-plan-active-enforcement-writable.md1004 B
  • chatgpt-plan-busy-composer-wait.md1008 B
  • chatgpt-plan-codex-web-indeterminate.md934 B
  • chatgpt-plan-codex-web-none-proven-unavailable.md1018 B
  • chatgpt-plan-codex-web-observed-inline-handoff.md986 B
  • chatgpt-plan-codex-web-observed-slash-handoff.md1.2 KB
  • chatgpt-plan-codex-web-refusal-docs-only.md1.3 KB
  • chatgpt-plan-desktop-standalone-transition.md1 KB
  • chatgpt-plan-explicitly-declined.md1.2 KB
  • chatgpt-plan-goal-and-plan-skill.md793 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.