agentmods.dev

loomkin AGENTS.md

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

In plain words
What is it for?
Use them when changing Loomkin's server, routes, authentication, shared project structure, formatting, tests, or pre-commit checks.
Why use it?
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.

Instructions file for CodexOpenCode

179 3mo ago A scan 686 tokens original MIT
View the source file pass-agent/loomkin
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 instructions/pass-agent/loomkin/agents-md
Clone the repo
git clone --depth 1 https://github.com/pass-agent/loomkin

Made for: Codex, OpenCode.

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. 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 $0.00686 $0.00686
Opus 5 $0.00343 $0.00343
Sonnet 5 $0.00137 $0.00137
Haiku 4.5 $0.00069 $0.00069

Measured 3d ago against content hash 8fad7c6f6d76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

  1. 3d 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 (179 stars, last pushed 3mo ago), licensed MIT. It adds 686 tokens to every session, about $0.0034 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.

LLMai-agentsbeamelixirgenserverliveview
Related

Other instructions, from other repositories

claude_code CLAUDE.md

Instructions for guess/claude_code, covering claude.md, project overview, common development commands, quality checks and testing.

guess/claude_code · 3,617 tokens

lang_ex AGENTS.md

Instructions for freshaengineering/lang_ex, covering langex, commands, architecture, behaviours and key design decisions.

freshaengineering/lang_ex · 3,305 tokens

raxol CLAUDE.md

Instructions for DROOdotFOO/raxol, covering claude.md, essential commands, initial setup, building & compilation and testing.

DROOdotFOO/raxol · 17,878 tokens

elixir-lsp CLAUDE.md

Claude Code instructions for zircote/elixir-lsp, covering claude.md, project overview, setup, key files and conventions.

zircote/elixir-lsp · 175 tokens

pi-elixir AGENTS.md

AGENTS.md instructions for elixir-vibe/pi-elixir, covering agent notes, planning, releases, local dogfooding and checks and integration tests.

elixir-vibe/pi-elixir · 1,626 tokens

lang_ex CLAUDE.md

Instructions for freshaengineering/lang_ex, a project described as: LangGraph for Elixir. Durable, human-in-the-loop LLM agents on the BEAM.

freshaengineering/lang_ex · 5 tokens