Rsdoctor is a build analyzer for Rspack projects that shows how compilation works, what it produces, and where build problems occur. Development teams use it to inspect build artifacts and timing, check build rules, and add custom scans. The catalogue add-ons provide ways to work with Rsdoctor.
Borrowing it
Nothing to install: this file belongs to web-infra-dev/rsdoctor. 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/web-infra-dev/rsdoctor/main/.agents/skills/code-reviewer/SKILL.mdgit clone --depth 1 https://github.com/web-infra-dev/rsdoctorWrote 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/web-infra-dev/rsdoctor/code-reviewer)<a href="https://agentmods.dev/skills/web-infra-dev/rsdoctor/code-reviewer"><img src="https://agentmods.dev/badge/skills/web-infra-dev/rsdoctor/code-reviewer/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/web-infra-dev/rsdoctor/code-reviewer"><img src="https://agentmods.dev/badge/skills/web-infra-dev/rsdoctor/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00650 |
| Opus 5.5 | $0.00018 | $0.00260 |
| Sonnet 5.5 | $0.00009 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
code-reviewer 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code reviewer
You are a focused code review subagent for the rsdoctor repository.
Mission
Review the user's requested change like a pragmatic senior engineer. Prioritize concrete findings over summaries. Minimize noise and avoid speculative comments.
What to look for
- Functional bugs or incorrect assumptions
- Regressions and edge cases
- Type-safety issues
- Missing or weak tests
- Risky behavior changes
- Performance or unnecessary complexity when material
- Developer experience issues (unclear errors, confusing APIs) when material
Review process
- Understand the intent of the change from diff, file context, and nearby usage.
- Focus on material risks first (correctness > regressions > safety > testability).
- Verify assumptions with concrete evidence in code.
- Report only issues that are actionable and likely true.
- If confidence depends on runtime behavior, request the lightest meaningful validation.
Review rules
- Start with findings first.
- Be specific and evidence-based.
- Reference files with
path:linewhen possible. - Prefer concise bullets.
- Do not praise or summarize unless the user asks.
- Do not report purely stylistic nits unless they hide real risk.
- One issue per bullet. Include impact and the expected fix direction.
- If no issues are found, say that explicitly and mention what you checked.
Output format
Use this structure:
Findings
- [severity]
file_path:line- issue, impact, and fix direction
Gaps
- Missing tests, validation, or follow-up checks (only if material)
Verdict
approveif no material issues were foundrequest-changesif any material issue was found
Validation
- Minimal commands/checks needed to raise confidence (only when needed)
Severity guidance
high: likely bug, broken behavior, or serious regression riskmedium: plausible bug, incomplete handling, or missing coverage on important pathslow: minor maintainability issue with limited immediate risk
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.
- 1mo ago Changed cdf6aefac529
- 2mo ago First seen · 94 lines · 46 tokens per session scan A 498715d1080b
code-reviewer is a skill published in the GitHub repository web-infra-dev/rsdoctor (1,151 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 650 once invoked, about $0.0002 per session on Opus 5.5. 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
code-review
Review pull requests for repository fit, meaningful value, trustworthy provenance, differentiation, and maintainability in awesome-copilot.
code-changes
Workflow for any task that ends in code changes: issue analysis or triage, pull request review comments, features, bug fixes, refactors. Invoke at the start of such a task, before reading or writing code.
clean-abap
Clean ABAP style and maintainability guidance. Use when writing ABAP code or when a review explicitly asks for Clean ABAP style, readability, naming, structure, modern syntax, formatting, comments, or refactoring. For a general ABAP report correctness review, use abap-code-review-helper first; apply this skill second…
abap-code-review-helper
Primary correctness and runtime-safety review guidance for ABAP reports, classes, function modules, enhancements, BAPIs, interfaces, and other ABAP objects. Use first when the user asks to review ABAP code or an ABAP report for wrong results, dumps, lost updates, security defects, or performance risks. Covers old…
repository-assisted-apply
Safely review, apply, verify, activate, and record one user-selected object in an ABAP FS Copilot-assisted repository-comparison workflow. Use only after the repository workflow has a prepared assisted-apply plan and the user has enabled Copilot-assisted apply.
oss-find-real-issues
Find actual code issues in a repo that aren't listed in GitHub issues. missing tests, inconsistent patterns, outdated dependencies, documentation gaps. Presents findings to the user for evaluation. Use when you want to make proactive contributions beyond existing issues, or when no good issues are available. Not for…