takazudo/gco
skills/gco/SKILL.md
Run GitHub Copilot CLI as a read-only sub-agent from Claude Code. Use when: (1) User says 'gco', 'copilot', or 'ask copilot', (2) Delegating code review or research to Copilot, (3) Getting a second opinion on code or architecture. Read-only mode (no file writes), claude-opus-4.6 model.
$ install --global
skillsauthnpx skillsauth add takazudo/claude-resources gcoInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 29, 2026, 4:44 AM181.7s5 files scanned
SKILL.md
- name:
- gco
- description:
- Run GitHub Copilot CLI as a read-only sub-agent from Claude Code. Use when: (1) User says 'gco', 'copilot', or 'ask copilot', (2) Delegating code review or research to Copilot, (3) Getting a second opinion on code or architecture. Read-only mode (no file writes), claude-opus-4.6 model.
- user-invocable:
- true
- argument-hint:
- <prompt>
GitHub Copilot Read-Only Sub-Agent
Run GitHub Copilot CLI in read-only mode for code review, research, and investigation tasks.
How It Works
- Copilot runs non-interactively with
-p(prompt) and-s(silent output) - Read-only enforced via
--deny-tool='write'(hard tool-level block) and read-only preamble in prompt - Uses
--no-ask-userand--allow-all-toolsfor fully autonomous execution - Model:
claude-opus-4.6(primary), auto-fallback togpt-4.1(free tier) on no-quota - Timeout: 15 minutes
Cheap variant
If you already know Premium quota is low and want to skip the opus attempt, use /gcoc instead — identical behavior but forces the free gpt-4.1 model from the start.
Process
Step 1: Build the Prompt
Take the user's request and use it as the copilot prompt. If the user provides /gco with arguments, use those as the prompt directly.
Step 2: Run Copilot
LOGDIR=$(node $HOME/.claude/scripts/get-logdir.js)
mkdir -p "$LOGDIR"
DATETIME=$(date +%Y%m%d_%H%M%S)
SLUG="<short-topic-slug>"
bash $HOME/.claude/skills/gco/scripts/gco-run.sh \
"<prompt>" \
"$LOGDIR/${DATETIME}-gco-${SLUG}.md" \
"$LOGDIR/${DATETIME}-gco-${SLUG}-stderr.log"
Run as a background Bash task with 15-minute timeout.
Step 3: Collect and Present Results
- Read the output file (
$LOGDIR/${DATETIME}-gco-${SLUG}.md) - If empty or missing, check stderr log for errors
- Check the stderr log for a
GCO_USED_FALLBACK=line. If present,gco-run.shauto-retried withgpt-4.1because the primary model was out of quota. Notify the user with one line: "Used gpt-4.1 instead of claude-opus-4.6 because of no quota." Proceed with the output — it is still valid. - Synthesize and present findings to the user
- Include the log file path for reference
Important Notes
- Copilot cannot modify files — all writes are done by Claude Code
- NEVER use
~in paths — use$HOME - Output and stderr go to
$LOGDIR/${DATETIME}-gco-*(timestamped) - If copilot is not installed, report "Copilot CLI not found. Install with: gh extension install github/gh-copilot" and fall back to Claude Code tools
Related Skills
takazudo/dev-linkify-cc-resources
development
VerifiedTrustedCommunity
Link Claude Code skill names mentioned in a CodeGrid article (data/{series}/{n}.md) to the author's public claude-resources repo, pinned to the latest commit hash so links don't rot. Use when: (1) user says 'linkify cc resources', 'link the skills', 'link skill names', or invokes /dev-linkify-cc-resources; (2) editing a CodeGrid article that mentions `/commits`, `/pr-complete`, `/skill-creator` or other Claude Code skills and they should point to claude-resources. Only links skills that actually exist in the public repo; skips hypothetical examples and code blocks.
10SKILL.mdUpdated Jun 2, 2026
takazudo/opus-2nd
development
VerifiedTrustedCommunity
Second opinion from Claude Opus on a plan or approach. Use when: (1) Planning phase of /big-plan needs a higher-quality review than /codex-2nd / /gco-2nd / /gcoc-2nd, (2) User says 'opus 2nd' or 'opus opinion', (3) Wanting Anthropic's larger model to critique a plan. Spawns a general-purpose Agent with model: opus that reads the plan file and returns structured feedback. Anthropic quota — not free.
10SKILL.mdUpdated May 29, 2026
takazudo/dev-ai-based-test
tools
VerifiedTrustedCommunity
AI-based testing via subagent + a per-task test-flow skill. Use when the user wants to verify something that mechanical assertions can't fully capture — image recognition, visual size/position comparison, animation smoothness, multi-step manual flows that need AI judgment. Triggers: 'AI-based test', 'AI test', 'visual verify', 'image recognition test', 'manual operation test', 'human-eye check', 'verify visually', 'compare screenshots', 'looks the same', 'looks correct'. The skill's job is to (1) author a focused test-flow skill that captures the exact procedure + verdict criteria, then (2) dispatch a verification subagent via the Agent tool that loads BOTH the test-flow skill AND a browser-driving skill (/verify-ui primary, /headless-browser fallback) so the subagent has clear context and consistent verdicts. NEVER uses `claude -p` — subagent dispatch goes through the Agent tool exclusively.
10SKILL.mdUpdated May 29, 2026
takazudo/cleanup-resources
development
VerifiedTrustedCommunity
End-of-workflow audit of touched GitHub issues, PRs, and branches via a Sonnet subagent. Use when: (1) /big-plan, /x-as-pr, or /x-wt-teams finishes its main work and needs to verify every touched resource is in the right state (closed when done, kept when ongoing, deleted when dead), (2) User says 'cleanup resources', 'audit cleanup', or 'check what should be closed', (3) A long workflow ends and the manager wants a structured paper trail of what it closed/kept/deleted. Auto-execute by default — the Sonnet agent proposes, the manager (you) executes safe actions and prints a final report.
10SKILL.mdUpdated May 29, 2026