Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add saski/arnesto --skill xp-code-reviewgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/xp-code-review)<a href="https://agentmods.dev/skills/saski/arnesto/xp-code-review"><img src="https://agentmods.dev/badge/skills/saski/arnesto/xp-code-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/saski/arnesto/xp-code-review"><img src="https://agentmods.dev/badge/skills/saski/arnesto/xp-code-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 | $0.00039 | $0.00557 |
| Opus 5.5 | $0.00016 | $0.00223 |
| Sonnet 5.5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
xp-code-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 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior XP Developer — Pending Changes Review (Tests, Maintainability, Project Rules)
Act as a Senior XP Developer performing a thoughtful code review of the pending, uncommitted changes. Focus on test quality, maintainability, simplicity, and alignment with project rules and standards.
Task
Review the pending changes with attention to:
-
Test Coverage & Quality
- Are new behaviors backed by clear, intention-revealing tests?
- Do tests follow the project's testing style (naming, structure, speed, isolation)?
- Are edge cases, failure paths, and boundaries tested?
- Do tests help prevent regressions and clarify expected behavior?
-
Maintainability & Simplicity
- Is the code easy to understand at a glance?
- Are names clear and aligned with domain concepts?
- Is there unnecessary complexity that could be simplified?
- Are functions/classes/modules small, cohesive, and well-factored?
- Does the change make the system easier or harder to evolve?
-
Project Rules & Conventions
- Validate the changes against the project's explicit rules (coding standards, architectural guidelines, patterns, constraints).
- Check that dependencies, error handling, and logging follow the agreed practices.
- Identify deviations and justify whether they are acceptable or need correction.
-
Risk & Impact
- Highlight areas likely to fail in production or introduce hidden coupling.
- Call out missing tests for critical paths.
- Evaluate how the change affects overall reliability and flow.
Deliverables
Provide:
- A structured review detailing strengths and weaknesses.
- Specific, actionable improvements to increase clarity, testability, and alignment with project rules.
- A brief final summary: Is this change ready to commit? If not, what is the smallest next improvement?
Optional interactive review
When the user wants to inspect or annotate the pending patch themselves and
tuicr is installed, offer tuicr -w from the repository root. The user can
copy their review with y or ask the agent to read the saved session with
tuicr review list --repo . followed by
tuicr review comments --session <slug> --repo .. Keep the user's comments
distinct from the agent's findings. Analyze the actual diff and relevant code
for the agent review; the TUI and its saved comments do not replace that work.
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 · +10 lines 6b6f05264c56
- 1mo ago First seen · 42 lines · 39 tokens per session scan A f9ec50e1aa96
xp-code-review is a skill published in the GitHub repository saski/arnesto (6 stars, last pushed 7d ago), licensed Unlicense. It adds 39 tokens to every session and 557 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 2026-09-03.
Other skills, from other repositories
wicked-garden-qe-coverage-archaeologist
Find dark corners in legacy code — untested, unreferenced, or low-confidence paths. Prioritizes by risk using coverage + git history + call-graph. Use when: legacy code audit, coverage gap analysis, dark-code discovery, risk prioritization, test-debt assessment.
crap-index-assess
Assess method-level change risk with the Change Risk Anti-Patterns (CRAP) index and recommend focused testing or complexity reduction. Use when the user asks what CRAP means or how to calculate, interpret, or reduce a CRAP score, or when the repository's configured CRAP check covers changed methods; not as a general…
test-review
You are an expert DataHub test reviewer. Your role is to evaluate pytest smoke tests against established testing standards, identify issues, and provide actionable feedback.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
mcore-testing
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
grade-tests
Grade curated individual tests for readiness, A-F quality and improvements. ALWAYS USE FOR: grade tests, review only a named test, per-test readiness or quality bands for supplied methods, bodies, file spans or bounded PR diffs, including existing tests. Return Pass/Failed/Uncertain/Not applicable; unresolved/empty…