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 ccarvalho-eng/codex-elixir-phoenix --skill elixir-phoenix-hexdocs-fetchergit clone --depth 1 https://github.com/ccarvalho-eng/codex-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/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-hexdocs-fetcher)<a href="https://agentmods.dev/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-hexdocs-fetcher"><img src="https://agentmods.dev/badge/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-hexdocs-fetcher/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/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-hexdocs-fetcher"><img src="https://agentmods.dev/badge/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-hexdocs-fetcher.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 | $0.00023 | $0.00653 |
| Opus 5.5 | $0.00009 | $0.00261 |
| Sonnet 5.5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
elixir-phoenix-hexdocs-fetcher 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HexDocs Fetcher
Efficiently fetch Elixir library documentation from hexdocs.pm using Codex web tools (web.search_query and web.open).
Usage
When researching libraries:
# Fetch library overview (known URL)
web.open("https://hexdocs.pm/oban")
# Fetch specific module docs
web.open("https://hexdocs.pm/phoenix_live_view/Phoenix.LiveView.html")
# Discover docs URL first, then open it
web.search_query("Oban.Worker site:hexdocs.pm")
web.open("{selected_result_url}")
Token Efficiency
Codex web tools extract page content so you can summarize key sections quickly:
| Source | Raw HTML | With Codex web tools | Benefit |
|---|---|---|---|
| HexDocs page | ~80k tokens | ~15k tokens | 80% reduction |
| Phoenix docs | ~120k tokens | ~25k tokens | 79% reduction |
| README | ~20k tokens | ~8k tokens | 60% reduction |
Integration with hex-library-researcher
When evaluating libraries, fetch docs efficiently:
web.open("https://hexdocs.pm/oban")
Common HexDocs URLs
# Library overview
https://hexdocs.pm/{library}
# Module documentation
https://hexdocs.pm/{library}/{Module}.html
https://hexdocs.pm/{library}/{Module.Submodule}.html
# Guides
https://hexdocs.pm/{library}/guides.html
https://hexdocs.pm/{library}/{guide-name}.html
# API reference
https://hexdocs.pm/{library}/api-reference.html
Extraction Strategies
Use focused extraction goals for better summaries:
# For API docs
Extract all public function docs with @spec and examples.
# For guides
Extract the complete guide content preserving code examples.
# For troubleshooting
Extract troubleshooting sections, common errors, and FAQs.
# For configuration
Extract configuration options and their defaults.
Caching
Codex may cache repeated fetches internally. Still prefer reusing prior notes within the same plan/research folder.
For longer persistence, save summaries under planning artifacts:
.codex/plans/{slug}/research/docs-oban.md
What ships with it
1 file 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 · 107 lines · 23 tokens per session scan A 3fd877ff506e
elixir-phoenix-hexdocs-fetcher is a skill published in the GitHub repository ccarvalho-eng/codex-elixir-phoenix (11 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 653 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
elixir-expert
Expert-level Elixir, Phoenix, OTP, and concurrent systems. Use when the user mentions Phoenix, OTP, Erlang, concurrent, or functional, or when the task involves Elixir Fundamentals or Phoenix Framework.
Elixir Patterns
Use this skill when working on Elixir/Phoenix projects and you want maintainable OTP-friendly structure, clear boundaries, and robust error handling.
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
python-repl
Interactive Python REPL automation with common helpers and best practices.
ax-cpp-ai
Use when writing C++ code with axllm for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.