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 agentmods add skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-compound-docsnpx skills add ccarvalho-eng/codex-elixir-phoenix --skill elixir-phoenix-compound-docsgit 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-compound-docs)<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>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 | $0.00021 | $0.00530 |
| Opus 5 | $0.00010 | $0.00265 |
| Sonnet 5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
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.
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
- ALWAYS search solutions before investigating — Check
.codex/solutions/for existing fixes before debugging - YAML frontmatter is MANDATORY — Every solution needs
validated metadata per
references/schema.md - One problem per file — Never combine multiple solutions
- 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-compoundcreates solution docs hereelixir-phoenix-investigatesearches here before debuggingelixir-phoenix-planconsults for known riskslearn-from-fixfeeds into this system
References
references/schema.md— YAML frontmatter validation schemareferences/resolution-template.md— Full solution template
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.
- 4d ago First seen · 85 lines · 21 tokens per session scan A d98709f29729
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.
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.
phoenix-framework
Use this skill working with Phoenix Framework. Consult this when working with the web layer, controllers, views, liveviews etc.
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…
code-review
Review code changes for regressions, correctness, and missing tests.
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…
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…