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 Miosa-osa/OSA --skill elixir-otpgit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/elixir-otp)<a href="https://agentmods.dev/skills/miosa-osa/osa/elixir-otp"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/elixir-otp/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/miosa-osa/osa/elixir-otp"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/elixir-otp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.00819 |
| Opus 5.5 | $0.00025 | $0.00328 |
| Sonnet 5.5 | $0.00012 | $0.00164 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
elixir-otp 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elixir and OTP: verify the code path
Workflow
- Read the repository instructions,
.tool-versions,mix.exs, and relevant existing modules/tests. Use its matched Elixir/OTP pair; runelixir --versionandmix --version. Do not hardcode another developer's installation path. - Read syntax and API examples for matching, guards, strings, maps, pipes, and error handling. Read OTP and integration pitfalls for servers, tasks, configuration, and Ecto.
- Verify external calls against the installed dependency source or its pinned
HexDocs version.
Code.ensure_loaded!/1followed byfunction_exported?/3checks functions; usemacro_exported?/3for macros. A missing module is not evidence that its documented API does not exist. - Write the smallest implementation following the project's conventions. Use explicit success/error return contracts at boundaries, validate external data, and keep arbitrary input as strings rather than creating atoms.
- Run
mix format --check-formatted,mix compile --warnings-as-errors, and the narrowest relevantmix test test/path_test.exs. Existing unrelated warnings must be reported accurately; a plain compile is not a warning-free check. - Exercise both success and failure paths. For OTP changes test the actual process, message ordering, timeout, and shutdown behavior. For persistence, assert a reread observes the change. A mock or compilation alone is not that evidence. Finish by reporting exact commands, outcomes, and uncovered cases.
Snippet verification
From this skill directory, run:
elixir references/verify_snippets.exs SKILL.md references/syntax.md references/gotchas.md
The verifier accepts trusted author-written snippets only; it executes code and
is not a sandbox for user-supplied programs. It requires Elixir 1.17 or newer.
elixir fences compile with no undefined-call warnings; elixir-run also calls
run/0 on defined modules (or executes a wrapped expression); elixir-bad must
fail compilation or emit an undefined-call warning. Runtime examples contain
assertions, so printing a plausible result is not considered success. Fences
must be self-contained; do not depend on definitions in a previous fence.
What ships with it
3 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.
- 1mo ago First seen · 76 lines · 62 tokens per session scan A 77cc1869208c
elixir-otp is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 62 tokens to every session and 819 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
bun-development
Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by oven-sh/bun.
python-patterns
Python design patterns, best practices, and idiomatic code.
typescript-expert
TypeScript best practices, advanced types, and patterns.
rust-patterns
Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
fastapi-patterns
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.