Mission control review tests
Skill MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-review-tests
Review Mission Control testing coverage and status. Use when the user wants to know what tests exist, what ran, what failed, what was skipped, or where validation coverage is still weak.From its SKILL.md
npx -y skills add MN755/Codex-Mission_Control --skill mission-control-review-testsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.9 KB, 342 tokens by cl100k_base, as published. Nobody here has run it
Mission Control Review Tests
Purpose
Summarize test coverage and validation status from Mission Control evidence.
The Codex chat agent is not the Mission Control Manager. It is the bridge between the user and the Mission Control Manager.
Use when
- The user asks about tests.
- A handoff needs test-focused review.
- Coverage and evidence quality need a status check.
Workflow
- Read validation-summary, handoff, and status resources.
- Identify available test commands, executed tests, skipped tests, failures, and gaps.
- Summarize recommended next tests if coverage is thin.
Mission Control calls
Tools:
mission_control_get_handoff_summarymission_control_get_status
Resources:
mission-control://projects/{project_id}/validation-summarymission-control://projects/{project_id}/handoffmission-control://projects/{project_id}/status
User-facing output
- Summarize available test commands, tests run, tests not run, failing tests, validation gaps, and recommended next tests.
- Highlight whether evidence is direct, dry-run, or missing.
Approval behavior
If the user wants new tests run and policy requires command approval, shift to the run-validation flow and preserve the approval gate.
Never do
- Do not grade coverage based on intuition alone.
- Do not hide missing evidence.
- Do not treat dry-run validation as equivalent to executed validation.
Failure and fallback
If dedicated validation resources are missing, build the summary from handoff evidence and current status, then clearly label any inference.
Example invocation
Review the test coverage and tell me what still needs validation.
What ships with it: 1 file
142 B alongside SKILL.md
agents/
- openai.yaml142 B