Borrowing it
Nothing to install: this file belongs to SoundBlaster/XcodeMCPWrapper. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SoundBlaster/XcodeMCPWrapper/main/.agents/skills/gh-pr-results-review/SKILL.mdgit clone --depth 1 https://github.com/SoundBlaster/XcodeMCPWrapperWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/soundblaster/xcodemcpwrapper/gh-pr-results-review)<a href="https://agentmods.dev/skills/soundblaster/xcodemcpwrapper/gh-pr-results-review"><img src="https://agentmods.dev/badge/skills/soundblaster/xcodemcpwrapper/gh-pr-results-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/soundblaster/xcodemcpwrapper/gh-pr-results-review"><img src="https://agentmods.dev/badge/skills/soundblaster/xcodemcpwrapper/gh-pr-results-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.00568 |
| Opus 5 | $0.00030 | $0.00284 |
| Sonnet 5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
gh-pr-results-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
GH PR Results Review
Workflow
- Identify the PR number and check status.
- Run:
gh pr checks <pr-number> 2>&1
- Capture failing checks, durations, run URL, and job URLs.
- If no failures exist, report success and stop.
- Resolve run and failing job IDs.
- Derive the workflow run ID from the run URL when available.
- Derive each failing job ID from job URLs, or list jobs with:
gh run view <run-id> --json jobs
- Pull logs for failed jobs.
- For each failed job:
gh run view <run-id> --job <job-id> --log 2>&1 | tail -80
- If the tail misses the error, inspect more lines or grep for error markers:
gh run view <run-id> --job <job-id> --log 2>&1 | rg -n "error|failed|traceback|E999|F401|mypy|pytest"
- Summarize root causes with evidence.
- Report by failing check/job name.
- Include the shortest exact evidence line(s) that explain failure.
- State likely fix direction (for example: ruff import ordering, mypy type mismatch, failing pytest assertion).
Output Format
Use this structure:
check the CI failure details.
Reviewed GitHub Actions logs for test and linting results
Bash
gh pr checks <pr-number> 2>&1
<key failing checks output>
Bash
gh run view <run-id> --job <job-id> --log 2>&1 | tail -60
<relevant error/failure excerpt>
Bash
gh run view <run-id> --job <job-id> --log 2>&1 | tail -40
<relevant error/failure excerpt>
Then provide a short diagnosis section:
Finding: one sentence per failed job.Evidence: command + key line.Next fix: concrete first edit to attempt.
Guardrails
- Do not claim a job failed without a log line proving it.
- Prefer job-specific logs over workflow-level summaries.
- Keep excerpts tight; include only lines needed to justify the finding.
- If GitHub CLI lacks permission or run is missing, state the blocker and requested access explicitly.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 72 lines · 61 tokens per session scan A b26615489c69
gh-pr-results-review is a skill published in the GitHub repository SoundBlaster/XcodeMCPWrapper (20 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 568 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
wcode
Use the wcode plugin and its MCP tools for repository coding, review, debugging, refactoring, architecture, Graph/Design inspection, safe edits, command execution, and verification. Trigger whenever wcode is installed or named, even when its tools are lazily registered or omitted from the host's initial tool list.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.