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 oliver-kriska/claude-elixir-phoenix --skill phx-reviewgit clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenixWrote 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/oliver-kriska/claude-elixir-phoenix/phx-review)<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/phx-review"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/phx-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/oliver-kriska/claude-elixir-phoenix/phx-review"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/phx-review.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 | $0.00032 | $0.01067 |
| Opus 5 | $0.00016 | $0.00534 |
| Sonnet 5 | $0.00006 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
phx-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 8d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Elixir/Phoenix Code
Perform an evidence-based, read-only review of changed code. Find and explain issues; do not edit files, create tasks, or fix findings.
Usage
phx-review
phx-review test
phx-review security
phx-review .claude/plans/auth/plan.md
phx-review --no-requirements
Treat the text after the skill name as a focus area, issue identifier, or path to a plan/specification.
Iron Laws
- Review is read-only — inspect and report; never modify the worktree.
- Scope to changed code — distinguish new defects from pre-existing issues.
- Every finding needs evidence — cite a path and line, explain impact, and describe the concrete failure mode.
- Check requirements when available — unmet requirements affect the verdict.
- Deduplicate and prioritize — one root cause is one finding, with the highest justified severity.
- Do not require custom agents, hooks, MCP, or unavailable task APIs — use optional runtime capabilities only when present.
Workflow
1. Establish Scope
Determine the merge base or user-specified base, then inspect:
git status --short
git diff --name-only <base>...HEAD
git diff --stat <base>...HEAD
git diff <base>...HEAD -- <changed-files>
Do not assume HEAD~5 is the correct base. Include uncommitted changes when the
user asks to review the current worktree. Record the chosen scope in the result.
2. Load Requirements
Unless --no-requirements is set, look for an explicit plan/spec path, current
conversation requirements, a branch or commit issue identifier, or the latest
relevant plan. Use available integrations or gh issue view when configured;
otherwise mark requirements NOT AVAILABLE and continue.
Read references/requirements-detection.md for detection order. Never let a
missing Linear, GitHub, hook, or MCP integration block code review.
3. Review by Concern
Select only concerns relevant to the diff:
- Elixir/Phoenix correctness and idioms;
- Ecto queries, changesets, transactions, migrations, and N+1 risks;
- LiveView lifecycle, reconnect, forms, streams, and assigns;
- authentication, authorization, secrets, and input handling;
- Oban idempotency, retries, uniqueness, and transaction boundaries;
- tests, regressions, and verification gaps;
- deployment/runtime configuration when those files changed.
What ships with it
6 files 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.
- 8d ago First seen · 126 lines · 32 tokens per session scan A 5a6dd10d6906
phx-review is a skill published in the GitHub repository oliver-kriska/claude-elixir-phoenix (544 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,067 once invoked, about $0.0002 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
121-java-object-oriented-design
Use when reviewing, improving, or refactoring Java object-oriented design, including applying SOLID, DRY, or YAGNI; improving classes and interfaces; correcting encapsulation, inheritance, or polymorphism; resolving God Class, Feature Envy, or Data Clumps; and improving object creation, methods, or exception…
053-design-simple-rules
Use when Java design, refactoring, or implementation tradeoffs should be evaluated with Kent Beck's simple design rules, including passes the tests, reveals intention, has no duplication, and has the fewest elements. This should trigger for requests such as Apply simple design rules; Review this design with Beck's…
craftcms
Craft CMS 5 plugin and module development — extending Craft with PHP. Covers elements, element queries, services, models, records, controllers, migrations, queue jobs, console commands, field types, native fields, events, behaviors, Twig extensions, widgets, filesystems, permissions, project config, GraphQL, testing…
craft-php-guidelines
Craft CMS 5 PHP coding standards and conventions. ALWAYS load when writing, editing, reviewing, or discussing any PHP in a Craft plugin or module — even small edits. Also when running ECS, PHPStan, or scaffolding with ddev craft make. Covers: PHPDoc blocks (@author, @since, @throws chains), section headers…
craft-pest
Testing Craft CMS 5 plugins and modules with Pest — test isolation, database safety, and the markhuot/craft-pest-core harness. ALWAYS load when writing, running, fixing, or reviewing tests for a Craft plugin or module, and whenever a suite touches a real Craft install. Covers why rollback is opt-in, tests/Pest.php +…
project-setup
Setup and hardening review for cross-platform modern-C++ (C++17) native projects, especially Node.js addons built with node-gyp / node-addon-api. Use when asked to "set up a native addon", "harden a C/C++ build", "review my binding.gyp", "add compiler hardening flags", "wire up AddressSanitizer/UBSan/TSan/clang-tidy"…