Mission control evidence check

Skill MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-evidence-check

Check whether Mission Control claims have backing evidence. Use when the user wants to know whether tests, builds, screenshots, artifacts, or handoff confidence are real, missing, weak, or dry-run only.From its SKILL.md

Install

npx -y skills add MN755/Codex-Mission_Control --skill mission-control-evidence-check

Assembled 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, 341 tokens by cl100k_base, as published. Nobody here has run it

Mission Control Evidence Check

Purpose

Audit evidence quality behind Mission Control claims and handoffs.

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 doubts a claim.
A handoff needs an evidence review.
Validation or artifact confidence matters before sign-off.

Workflow

Review handoff, validation, and status resources.
Identify tests claimed but not run, builds claimed without output, missing screenshots or artifacts, dry-run-only evidence, and weak confidence signals.
Summarize what is backed and what still needs proof.

Mission Control calls

Tools:

mission_control_get_handoff_summary
mission_control_get_status

Resources:

mission-control://projects/{project_id}/handoff
mission-control://projects/{project_id}/validation-summary
mission-control://projects/{project_id}/status

User-facing output

Call out weak evidence clearly and identify the concrete missing artifact or validation step.
Differentiate between executed evidence and dry-run or inferred evidence.

Approval behavior

If the fix is to run additional validation that requires commands, preserve the normal approval flow.

Never do

Do not let evidence-free claims pass as verified.
Do not overstate confidence.
Do not treat dry-run as proof of execution.

Failure and fallback

If evidence-specific resources are limited, inspect handoff and validation summaries, mark any inference explicitly, and note which dedicated evidence surfaces are expected or future.

Example invocation

Check whether the Mission Control handoff claims are actually backed by evidence.

What ships with it: 1 file

134 B alongside SKILL.md

agents/

openai.yaml134 B