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 AmariahAK/atlarix-skills --skill code-reviewgit clone --depth 1 https://github.com/AmariahAK/atlarix-skillsWrote 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/amariahak/atlarix-skills/code-review)<a href="https://agentmods.dev/skills/amariahak/atlarix-skills/code-review"><img src="https://agentmods.dev/badge/skills/amariahak/atlarix-skills/code-review.svg" alt="Measured on agentmods" 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 | $0.00002 | $0.00748 |
| Opus 5 | $0.00001 | $0.00374 |
| Sonnet 5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review (Structured)
When to use this skill
Use this skill when reviewing a PR or a set of changes and you want a consistent, production-grade review pass: security first, then correctness, then performance, then style.
Core patterns
Review in passes (order matters)
- Security: injection, auth, secrets, validation
- Correctness: edge cases, nullability, error handling, idempotency
- Performance: N+1, unnecessary re-renders, large allocations, slow queries
- Readability: naming, structure, complexity, comments that explain why
Security checklist
- Input validation at boundaries (HTTP, CLI, IPC)
- Parameterized queries (no SQL concat)
- AuthZ checks (not just auth)
- No secrets committed/logged
- Safe file paths (no path traversal)
Correctness checklist
- Error paths handled (and user sees useful errors)
- Off-by-one / null / undefined cases covered
- Async operations awaited and cancellable where needed
- Invariants enforced (types + runtime guards)
Performance checklist
- Avoid N+1 query loops
- Avoid loading entire files/blobs when a slice will do
- For React: avoid unnecessary re-renders and huge client bundles
Correctness in distributed systems (quick reminders)
- Retries must be bounded and idempotent
- Timeouts should exist on network calls
- Errors should propagate with enough context to act
Review output expectations
Good review comments include:
- risk (“this can break when…”)
- evidence (line reference / concrete scenario)
- suggestion (what to change or test)
Suggesting tests (high leverage)
When you see risk, ask for one of:
- a unit test for pure logic
- an integration test for wiring
- an e2e test for user-critical flows
Readability checklist
- Names match domain meaning
- Small focused functions
- Comments explain intent/tradeoffs, not narration
What NOT to nitpick
- formatting (use formatter/linter)
- minor style preference that doesn’t impact maintainability
- “rewrite in my style” feedback
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.
- 4d ago First seen · 101 lines · 2 tokens per session scan A 00a7a686acd1
Code Review is a skill published in the GitHub repository AmariahAK/atlarix-skills (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 2 tokens to every session and 748 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.
code-review
Reviews code snippets and provides improvement suggestions.
code-review
Comprehensive code review for security, performance, and best practices.
quality-gate
Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, and test updates. Use when running quality checks before a PR.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
sol-luna-router
Route substantial coding or repository-review work through a two-stage Sol commander/verifier and separate Luna Max CLI worker. Use when the user explicitly asks Sol to direct or supervise Luna, explicitly requests this router, needs an isolated auditable Luna-owned implementation with a Sol review loop, or asks to…