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 pproenca/dot-skills --skill adversarial-elixirgit clone --depth 1 https://github.com/pproenca/dot-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/pproenca/dot-skills/adversarial-elixir)<a href="https://agentmods.dev/skills/pproenca/dot-skills/adversarial-elixir"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/adversarial-elixir.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Anti-Refusal · line 51 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00218 | $0.01913 |
| Opus 5 | $0.00109 | $0.00957 |
| Sonnet 5 | $0.00044 | $0.00383 |
| Haiku 4.5 | $0.00022 | $0.00191 |
Grade A, and why
adversarial-elixir 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Elixir Gate
An Elixir/OTP/Ecto/Phoenix review gate — pass/fail: a single blind reviewer subagent judges the work against this gate's rules with an adversarial mandate, and the work passes only when every rule is PASS or N/A. This skill renders verdicts; it never fixes the work.
The rules target one failure mode: code that imported the wrong mental model onto the BEAM — OO/enterprise layering, processes treated as objects, anemic data, defensive control flow, transliterated loops, and needless metaprogramming. They are grounded in the official Elixir anti-pattern catalogs and each carries an Evidence of violation paragraph so a reviewer can decide PASS/FAIL/N/A from artifact evidence alone. Judgment-call refactor guidance stays in the advisory sibling staff-level-elixir.
When to Apply
- An Elixir diff, feature, or PR is about to merge and needs an objective PASS/FAIL, not advisory feedback.
- An agent (Claude, Codex) authored the code and you want an independent check that it did not reproduce OO habits — repository wrappers over Ecto,
*Service/*Managertiers, a GenServer per entity, DI behaviours for a single implementation, raise/rescue as anif. - Code ported from Java/Ruby/Python (or written by developers newer to the BEAM) needs auditing for paradigm fit before it calcifies.
- A refactor claims to have "made it idiomatic" and you want the claim verified, not assumed.
Do not apply to non-Elixir codebases (the reviewer prompt's precondition aborts with "GATE NOT APPLICABLE"), or when the user wants explanations and refactors rather than a verdict — that is staff-level-elixir's job. arch-delete-repository-over-ecto goes N/A when the target has no Ecto; flow-normalize-at-boundary goes N/A when the target has no external-input path. Remedies newer than the project's Elixir version are judged against the nearest available remedy — the reviewer prompt carries the version-gate table.
Review Protocol
Follow these steps exactly — the gate's value is that every review runs the same way.
What ships with it
24 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.
- assets/templates/verdict.md 1.5 KB
- gotchas.md 3.1 KB
- metadata.json 1.4 KB
- references/_sections.md 3.5 KB
- references/arch-context-over-service-objects.md 2.0 KB
- references/arch-delete-repository-over-ecto.md 2.1 KB
- references/arch-drop-di-behaviour-single-impl.md 2.3 KB
- references/arch-functional-core-imperative-shell.md 2.4 KB
- references/flow-assertive-over-defensive.md 2.4 KB
- references/flow-no-exceptions-for-control.md 2.9 KB
- references/flow-normalize-at-boundary.md 2.1 KB
- references/iter-named-combinator-over-manual-loop.md 2.5 KB
- references/meta-functions-not-macro-dsl.md 2.1 KB
- references/meta-no-compile-time-coupling.md 1.9 KB
- references/meta-use-is-not-import.md 1.9 KB
- references/proc-consolidate-interface.md 1.9 KB
- references/proc-no-process-as-variable.md 2.2 KB
- references/proc-no-singleton-manager.md 2.1 KB
- references/proc-not-objects.md 2.2 KB
- references/reviewer-prompt.md 6.3 KB
- references/type-protocol-over-type-dispatch.md 2.2 KB
- references/type-split-god-struct.md 1.8 KB
- references/type-struct-over-bare-map.md 1.9 KB
- references/type-tagged-state-over-flags.md 2.0 KB
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 · 67 lines · 218 tokens per session scan A 4c0f63cbf379
adversarial-elixir is a skill published in the GitHub repository pproenca/dot-skills (203 stars, last pushed 23d ago), licensed MIT. It adds 218 tokens to every session and 1,913 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…