elixir-phoenix-compound-docs

elixir-phoenix-compound-docs is a skill for Claude Code, Codex from ccarvalho-eng/codex-elixir-phoenix. It costs 21 tokens per session (530 once invoked), scanned A, original, MIT.

A searchable collection of past solutions for debugging Elixir and Phoenix projects, stored as one documented problem per file.

In plain words
What is it for?
Use it to search past solutions before debugging issues involving Phoenix, Ecto, LiveView, Oban, OTP, security, testing, deployment, performance, or builds.
Why use it?
It prevents repeating investigations that have already been solved and preserves the reasoning behind earlier fixes. Each record also includes symptoms, causes, metadata, and prevention advice.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-compound-docs
Any agent
npx skills add ccarvalho-eng/codex-elixir-phoenix --skill elixir-phoenix-compound-docs
Clone the repo
git clone --depth 1 https://github.com/ccarvalho-eng/codex-elixir-phoenix

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for elixir-phoenix-compound-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-compound-docs.svg)](https://agentmods.dev/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-compound-docs)
Your own site
<a href="https://agentmods.dev/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-compound-docs"><img src="https://agentmods.dev/badge/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-compound-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00530
Opus 5 $0.00010 $0.00265
Sonnet 5 $0.00004 $0.00106
Haiku 4.5 $0.00002 $0.00053

Measured 4d ago against content hash d98709f29729, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

elixir-phoenix-compound-docs 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 4d 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.

skills/elixir-phoenix-compound-docs/SKILL.md · 85 lines

What it actually says

Compound Docs — Institutional Knowledge Base

Searchable, categorized solution documentation that makes each debugging session easier than the last.

Directory Structure

.codex/solutions/
├── ecto-issues/
├── liveview-issues/
├── oban-issues/
├── otp-issues/
├── security-issues/
├── testing-issues/
├── phoenix-issues/
├── deployment-issues/
├── performance-issues/
└── build-issues/

Iron Laws

  1. ALWAYS search solutions before investigating — Check .codex/solutions/ for existing fixes before debugging
  2. YAML frontmatter is MANDATORY — Every solution needs validated metadata per references/schema.md
  3. One problem per file — Never combine multiple solutions
  4. Include prevention — Every solution documents how to prevent recurrence

Solution File Format

---
module: "Accounts"
date: "2025-12-01"
problem_type: runtime_error
component: ecto_schema
symptoms:
  - "Ecto.Association.NotLoaded on user.posts"
root_cause: missing_preload
severity: medium
tags: [preload, association, n-plus-one]
---

# Association NotLoaded on User Posts

## Symptoms
Ecto.Association.NotLoaded raised when accessing user.posts
in UserListLive after filtering.

## Root Cause
Query in Accounts context missing preload for :posts.

## Solution
Added `Repo.preload(:posts)` to `list_users/1`.

## Prevention
Use n1-check skill before shipping list views.

Searching Solutions

Use rg to search .codex/solutions/ by symptom (e.g., NotLoaded), by tag (e.g., tags:.*preload), or by component (e.g., component: ecto).

Integration

  • elixir-phoenix-compound creates solution docs here
  • elixir-phoenix-investigate searches here before debugging
  • elixir-phoenix-plan consults for known risks
  • learn-from-fix feeds into this system

References

  • references/schema.md — YAML frontmatter validation schema
  • references/resolution-template.md — Full solution template
Files

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.

Changes

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.

  1. 4d ago First seen · 85 lines · 21 tokens per session scan A d98709f29729

Subscribe to this mod's changes

elixir-phoenix-compound-docs is a skill published in the GitHub repository ccarvalho-eng/codex-elixir-phoenix (11 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 530 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

ash-framework

Use this skill working with Ash Framework or any of its extensions. Always consult this when making any domain changes, features or fixes.

agentjido/jido_managed_agents · 29 tokens

phoenix-framework

Use this skill working with Phoenix Framework. Consult this when working with the web layer, controllers, views, liveviews etc.

agentjido/jido_managed_agents · 29 tokens

writing-review-packets

Create or revise Reviews packet markdown for a code diff, including section strategy, prose, hunk references, validation, and pushing packet revisions with the Reviews CLI. Use when the user asks to write a review packet, organize a diff for review, add prose around hunk refs, update a packet for a new patchset, or…

figitaki/reviews · 82 tokens

code-review

Review code changes for regressions, correctness, and missing tests.

agentjido/jido_managed_agents · 16 tokens

using-reviews-locally

Run and use the Reviews app locally, including server startup, port checks, local token setup, CLI config, pushing local reviews or new patchsets, and Codex workflow conventions. Use when the user asks to spin up Reviews, push a local review packet or revision, mint/access local API tokens, debug localhost review…

figitaki/reviews · 82 tokens

reviews-overview

Explain the Reviews platform to a general agent: what Reviews provides, when to use it during human-in-the-loop or agent-driven development, how review packets structure a diff for humans, and how Reviews can precede public PR creation or integrate with other review processes. Use when an agent needs to decide whether…

figitaki/reviews · 85 tokens