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 challengegit 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/challenge)<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/challenge"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/challenge.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 14 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 14 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00034 | $0.01117 |
| Opus 5 | $0.00017 | $0.00558 |
| Sonnet 5 | $0.00007 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
challenge 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 5d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- phx-challenge — 91% identical, 18 lines differ
- elixir-phoenix-challenge — 86% identical, 20 lines differ
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Challenge Mode Reviews
Rigorous, critical review patterns inspired by Boris Cherny's "Grill me" approach. Push beyond first solutions to ensure quality.
Iron Laws - Never Violate These
- No approval without verification - Don't approve until all concerns addressed
- Assume bugs exist - Look for edge cases, race conditions, missing handlers
- Question everything - Even "obvious" code can hide issues
- Demand proof - Ask for tests, show state transitions, verify behavior
Adversarial Lenses (Apply to ALL Modes)
- "What Would Break This?" — Production failure modes under load, during deploys, with unexpected data
- "Assumption Stress Test" — List every assumption; which are most fragile?
- "Contradictions Finder" — Find contradictions between tests/implementation, docs/behavior, or within the changeset
Challenge Modes
Ecto Challenge (/phx:challenge ecto)
Grill the developer on database changes:
Migration Safety
- Will this migration lock the table in production?
- What happens to existing records without the new field?
- Is the migration reversible?
- Are there any unsafe operations (column removal, type change)?
Query Performance
- Have you introduced any N+1 queries?
- Are there missing indexes for new WHERE clauses?
- Will this query scale with data growth?
Schema Integrity
- Are all constraints enforced at database level?
- What happens during rolling deployment (old code, new schema)?
- Are foreign key cascades correct?
Backward Compatibility
- Will old code work during deployment?
- Are there any breaking changes to the context API?
LiveView Challenge (/phx:challenge liveview)
Prove the LiveView handles all cases:
Event Coverage
- List every
handle_eventclause and expected socket state - What happens if socket assigns are missing when event fires?
- Are there race conditions between user events and server pushes?
PubSub Handling
- List every
handle_infoclause and when it's triggered - Do all PubSub subscriptions have corresponding handlers?
- What happens if a message arrives before mount completes?
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.
- 5d ago First seen · 150 lines · 34 tokens per session scan A 84961bd496d7
challenge is a skill published in the GitHub repository oliver-kriska/claude-elixir-phoenix (541 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 1,117 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
elderly-ui-audit
A code review for making websites and mobile apps easier for older people to use, based on Chinese government accessibility guidelines.
fable-super-audit
Comprehensive, rubric-driven, whole-repository code audit that ends in a prioritized improvement plan with an executive health grade. Built to run in a premium, time-limited model session (Fable): it dispatches cheaper Opus/Sonnet subagents to explore the codebase and pre-build a project-tailored audit checklist, then…
cc-codex-review
A second-opinion workflow that sends uncertain questions and important technical decisions to Codex for review alongside Claude Code.
skill-pr-review
Comprehensive code review for pull requests using parallel multi-agent analysis. Audits CLAUDE.md compliance, checks for bugs, analyzes git history, reviews comments, and filters by confidence score. Use when reviewing a GitHub PR, mentions "code review", "review this PR", or "/code-review".
improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
odoo-code-review
Use when reviewing Odoo code — yours before commit, Claude's after generation, or a teammate's PSDU PR. Catches shape-of-bad-code issues that lint won't, plus customer-readiness gaps. Invoke before claiming Odoo work is done.