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 elixir-meta-programminggit 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/elixir-meta-programming)<a href="https://agentmods.dev/skills/pproenca/dot-skills/elixir-meta-programming"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/elixir-meta-programming/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/pproenca/dot-skills/elixir-meta-programming"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/elixir-meta-programming.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 | $0.00167 | $0.01418 |
| Opus 5 | $0.00084 | $0.00709 |
| Sonnet 5 | $0.00033 | $0.00284 |
| Haiku 4.5 | $0.00017 | $0.00142 |
Grade A, and why
elixir-meta-programming 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elixir Metaprogramming & DSLs
How to build Elixir macros and declarative DSLs correctly — for the case where a macro is genuinely warranted and a plain function won't do. Each rule corrects a specific wrong default a capable model makes once it starts writing quote/unquote, __using__, and @before_compile; nothing here restates macro basics the model already knows.
First: is a macro actually warranted?
The default answer is no — reach for a higher-order function, a behaviour, or data-plus-an-interpreter first. That gate is not this skill's job; it lives in the sibling skills and you should apply it before opening this one:
staff-level-elixir→data-functions-over-macros(solve it with a function first)adversarial-elixir→meta-functions-not-macro-dsl,meta-use-is-not-import,meta-no-compile-time-coupling
A macro earns its place only when you need something a function cannot give — new syntax, control over whether/when arguments evaluate, or code that must exist at compile time (compiling a schema, generating clauses from a declaration list). Once you've crossed that threshold, this skill is how you do it right.
When to Apply
- Writing a macro — deciding what goes in the
quoteblock versus a runtime function, and how arguments evaluate - Building a declarative DSL — a
schema/spec/route/workflowblock that collects declarations and generates a module - Wiring
use MyDSL— what__using__should inject and what belongs in@before_compile - Generating functions or clauses from a list of declarations at compile time
- Making a DSL fail at
mix compilewith an error that points at the user's source - Reviewing existing macro/DSL code for evaluation, hygiene, escaping, and compile-time-validation bugs
Rule Categories
| # | Category | Prefix | Covers |
|---|---|---|---|
| 1 | Macro Design | macro |
The shape of a single macro — thin macro over a runtime function; defguard for guard-safe constructs |
| 2 | Quote & Hygiene | quote |
Compile-time semantics traps — multiple evaluation, Macro.escape, hygiene vs var! |
| 3 | DSL Construction | dsl |
Assembling a block DSL — accumulating attributes + @before_compile, minimal __using__, unquote fragments, introspection |
| 4 | Compile-Time Validation | valid |
Failing well — validate while compiling, locate errors at the caller's line |
What ships with it
15 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.
- AGENTS.md 3.5 KB
- assets/templates/_template.md 1.0 KB
- metadata.json 1.1 KB
- references/_sections.md 2.2 KB
- references/dsl-accumulate-attributes.md 2.0 KB
- references/dsl-introspection-function.md 1.4 KB
- references/dsl-unquote-fragments.md 1.2 KB
- references/dsl-using-minimal.md 1.2 KB
- references/macro-defguard-for-guards.md 1.2 KB
- references/macro-thin-delegate-runtime.md 1.5 KB
- references/quote-bind-quoted-single-eval.md 1.4 KB
- references/quote-escape-runtime-data.md 1.2 KB
- references/quote-rely-on-hygiene.md 1.5 KB
- references/valid-fail-at-compile-time.md 1.4 KB
- references/valid-locate-errors-at-caller.md 1.7 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.
- 5d ago First seen · 82 lines · 167 tokens per session scan A 8610e3dc4778
elixir-meta-programming is a skill published in the GitHub repository pproenca/dot-skills (205 stars, last pushed 24d ago), licensed MIT. It adds 167 tokens to every session and 1,418 once invoked, about $0.0008 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
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
platform-detection
Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system. Use only for "which test platform/framework?", "VSTest or MTP?", or "what runner does this project use?", including bridge settings, UseVSTest opt-outs, and incompatible or conflicting VSTest/MTP configuration.…
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
omh-rust
This is a Hermes-native rust workflow skill.
axiom-concurrency
Use when writing ANY async code, actors, threads, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.