From claude-resources
Gets a second opinion from GitHub Copilot CLI on plans or approaches during /x-as-pr or /x-wt-teams planning. Returns actionable feedback or gracefully skips if unavailable.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-resources:gco-2ndThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Get a second opinion from GitHub Copilot CLI on a plan, approach, or codebase exploration.
Get a second opinion from GitHub Copilot CLI on a plan, approach, or codebase exploration.
Before doing anything, check if Copilot is currently in degraded mode:
RATE_CHECK=$(node $HOME/.claude/scripts/gco-rate-limit.js check 2>&1)
If the output starts with degraded:, notify the user that Copilot is in low-cost mode (auto-downgraded model) but proceed with Copilot anyway — it is still usable. Do NOT skip.
Construct a prompt that includes:
You are reviewing a development plan. Provide a second opinion.
## Context
<what the project is, what repo we're in>
## Current Plan
<the plan or approach being considered>
## Questions
1. Are there any risks, edge cases, or issues with this approach?
2. Is there a simpler or better alternative?
3. Are there any files or areas of the codebase that should be considered but aren't mentioned?
4. Any other suggestions or concerns?
Be concise and practical. Focus on actionable feedback. If the plan looks solid, say so briefly — don't invent problems.
LOGDIR=$(node $HOME/.claude/scripts/get-logdir.js)
mkdir -p "$LOGDIR"
DATETIME=$(date +%Y%m%d_%H%M%S)
bash $HOME/.claude/skills/gco/scripts/gco-run.sh \
"<prompt>" \
"$LOGDIR/${DATETIME}-gco-2nd.md" \
"$LOGDIR/${DATETIME}-gco-2nd-stderr.log"
Timeout: 15 minutes.
Return the Copilot feedback to the caller. The caller decides whether to incorporate it into the plan.
No fallback needed. If Copilot fails, skip — the plan proceeds without the second opinion. This is advisory, not critical.
~ in paths — use $HOMEnpx claudepluginhub takazudo/claude-resources --plugin claude-resourcesGets a second opinion from OpenAI Codex CLI during planning to validate approaches, identify risks, and suggest alternatives.
Consults Codex CLI for second opinions on code reviews, designs, or implementations by crafting context-based prompts, executing via bash with configurable depth (light/normal/deep), and summarizing results.
Cross-model review using OpenAI Codex to independently verify plans or code diffs, iterating up to 5 rounds. Useful for architecture decisions, non-trivial refactors, and critical config changes.