What is loomkin AGENTS.md?

Project instructions for Loomkin, including its repository layout, coding checks, commit naming, authentication rules, and commands for an Elixir/Phoenix server.

Use them when changing Loomkin's server, routes, authentication, shared project structure, formatting, tests, or pre-commit checks.

They give coding agents project-specific rules that general instructions would not know, including where commands run and which routes need authentication. An Elixir/Phoenix app is a web application built with the Elixir language and Phoenix framework.

How pass-agent/loomkin configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to pass-agent/loomkin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/pass-agent/loomkin/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/pass-agent/loomkin

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pass-agent/loomkin/agents-md/github.svg)](https://agentmods.dev/instructions/pass-agent/loomkin/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/pass-agent/loomkin/agents-md"><img src="https://agentmods.dev/badge/instructions/pass-agent/loomkin/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pass-agent/loomkin/agents-md"><img src="https://agentmods.dev/badge/instructions/pass-agent/loomkin/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 686 This file is loaded in full into every session.

When invoked 686 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00686	$0.00686
Opus 5.5	$0.00274	$0.00274
Sonnet 5.5	$0.00137	$0.00137
Haiku 4.5	$0.00069	$0.00069

Measured 2mo ago against content hash 8fad7c6f6d76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

loomkin AGENTS.md 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 2mo 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.

AGENTS.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loomkin - AI Instructions

Read and follow CONTRIBUTING.md for all conventions, including commit message format, build commands, and code style.

Monorepo Layout

loomkin-server/ — Elixir/Phoenix app (mix.exs, lib/, config/, priv/, test/, assets/)
apps/ — Client applications (desktop, mobile) — future
packages/ — Shared JS/TS libraries — future
services/ — Polyglot backend services — future

All mix commands must be run from the loomkin-server/ directory (or use make targets from root).

Key reminders:

Commit subjects must be fully lowercase (no acronyms like UI or API — use ui, api)
Run cd loomkin-server && mix format before committing
Run cd loomkin-server && mix precommit to validate everything before pushing
Never run slow commands (e.g. mix test, mix precommit, mix compile) without piping output to a /tmp log file (e.g. mix test 2>&1 | tee /tmp/mix_test.log). This avoids rerunning the entire command just to grep for a specific string — search the log file instead.

Authentication

Always handle authentication flow at the router level with proper redirects
Always be mindful of where to place routes. phx.gen.auth creates multiple router plugs:
- A plug :fetch_current_scope_for_user that is included in the default browser pipeline
- A plug :require_authenticated_user that redirects to the log in page when the user is not authenticated
- In both cases, a @current_scope is assigned to the Plug connection
- A plug redirect_if_user_is_authenticated that redirects to a default path in case the user is authenticated - useful for a registration page that should only be shown to unauthenticated users
Always let the user know in which router scopes and pipeline you are placing the route, AND SAY WHY
phx.gen.auth assigns the current_scope assign - it does not assign a current_user assign
Always pass the assign current_scope to context modules as first argument. When performing queries, use current_scope.user to filter the query results
To derive/access current_user in templates, always use the @current_scope.user, never use @current_user in templates
Anytime you hit current_scope errors or the logged in session isn't displaying the right content, always double check the router and ensure you are using the correct plug as described below

Read the full file on GitHub · 51 lines

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.

2mo ago First seen · 51 lines · 686 tokens per session scan A 8fad7c6f6d76

Subscribe to this mod's changes

loomkin AGENTS.md is an instructions file published in the GitHub repository pass-agent/loomkin (182 stars, last pushed 5mo ago), licensed MIT. It adds 686 tokens to every session, about $0.0027 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.

Building agents LLM ai-agents beam elixir genserver liveview

loomkin AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
loomkin AGENTS.mdpass-agent/loomkin	Instructions file	182	5mo ago	MIT	A	686	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

loomkin: Instructions file for Codex