Imported from MN755/Codex-Mission_Control (.codex/plugins/mission-control/skills/mission-control-benchmark-comparison/SKILL.md). Install upstream with npx skills add MN755/Codex-Mission_Control --skill mission-control-benchmark-comparison. Copyright stays with the author.

Mission Control Benchmark Comparison

Name: mission-control-benchmark-comparison
Author: MN755

Purpose

Use Mission Control to compare GPU benchmark results before and after code changes with explicit evidence and known variance.

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 whether a CUDA change made things faster.
A kernel optimization needs before-and-after comparison.
Performance work risks trading away correctness or stability.

Workflow

Read the current validation summary and diagnostics.
Ask Mission Control to identify the benchmark path that matches the changed code.
Keep the benchmark loop paired with focused correctness validation.
Record the delta and the confidence level honestly.
Feed the result back into optimization, review, or handoff output.

Mission Control calls

Tools:

mission_control_start_task
mission_control_get_status
mission_control_get_handoff_summary

Resources:

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

User-facing output

Show the benchmark target and the claimed delta.
Show whether the evidence supports speedup, regression, or inconclusive results.
Show whether infrastructure issues contaminated the run.

Approval behavior

Benchmark commands and any supporting build or profile steps still use Mission Control approval rules.

Never do

Do not compare unmatched workloads.
Do not call noisy or one-off results a win.
Do not hide correctness regressions behind faster numbers.

Failure and fallback

If the repo has no clear benchmark target, say that plainly and fall back to a focused profiling or validation task first.

Example invocation

Use Mission Control to compare the current GPU benchmark against the previous baseline.

{ "ocm": "1", "id": "mn755-codex-mission-control-mission-control-benchmark-co-6ba352", "kind": "skill", "name": "mission-control-benchmark-comparison", "description": "Compare before-and-after performance evidence through Mission Control without turning benchmark claims into theater.", "publisher": "MN755", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Compare before-and-after performance evidence through Mission Control without turning benchmark claims into theater." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/MN755/Codex-Mission_Control", "path": ".codex/plugins/mission-control/skills/mission-control-benchmark-comparison/SKILL.md", "ref": "7349825e52b9cf41417eedd82aec6e6a762aabff", "url": "https://github.com/MN755/Codex-Mission_Control/blob/7349825e52b9cf41417eedd82aec6e6a762aabff/.codex/plugins/mission-control/skills/mission-control-benchmark-comparison/SKILL.md", "key": "MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-benchmark-comparison/SKILL.md" } }, "instructions": "# Mission Control Benchmark Comparison\n\n## Purpose\n\nUse Mission Control to compare GPU benchmark results before and after code changes with explicit evidence and known variance.\n\nThe Codex chat agent is not the Mission Control Manager. It is the bridge between the user and the Mission Control Manager.\n\n## Use when\n\n- The user asks whether a CUDA change made things faster.\n- A kernel optimization needs before-and-after comparison.\n- Performance work risks trading away correctness or stability.\n\n## Workflow\n\n1. Read the current validation summary and diagnostics.\n2. Ask Mission Control to identi", "cost": { "context_tokens": 483 } }

mission-control-benchmark-comparison

About