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/dilolabs/nosia/model-patternsnpx skills add dilolabs/nosia --skill model-patternsgit clone --depth 1 https://github.com/dilolabs/nosiaWhat 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 | $0.00078 | $0.01938 |
| Opus 5 | $0.00039 | $0.00969 |
| Sonnet 5 | $0.00016 | $0.00388 |
| Haiku 4.5 | $0.00008 | $0.00194 |
Grade A, and why
model-patterns 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 2d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Patterns (37signals)
Rich domain models over service objects. Business logic lives in models, not in separate service classes.
Project knowledge
Tech Stack: Rails 8.2 (edge), UUIDs everywhere, database-backed everything (no Redis) Patterns: Heavy use of concerns, default values via lambdas, Current for context
Commands:
bin/rails generate model Card title:string body:text board:references:uuid
bin/rails generate migration AddColorToCards color:string
bin/rails db:migrate
bin/rails test test/models/
bin/rails console
Rich model vs service object
# BAD -- service object
class CloseCardService
def initialize(card, user)
@card = card
@user = user
end
def call
ActiveRecord::Base.transaction do
@card.create_closure!(user: @user)
@card.track_event("card_closed", user: @user)
end
end
end
# GOOD -- rich model
class Card < ApplicationRecord
include Closeable
def close(user: Current.user)
create_closure!(user: user)
track_event "card_closed", user: user
notify_recipients_later
end
end
# Controller simply calls:
@card.close
Model structure
Order within a model:
class Card < ApplicationRecord
# 1. Concern includes
include Assignable, Closeable, Eventable, Searchable, Watchable
# 2. Associations
belongs_to :account, default: -> { board.account }
belongs_to :board, touch: true
belongs_to :column, touch: true
belongs_to :creator, class_name: "User", default: -> { Current.user }
has_many :comments, dependent: :destroy
has_many :assignments, dependent: :destroy
has_one :closure, dependent: :destroy
# 3. Validations
validates :title, presence: true
validates :status, inclusion: { in: %w[draft published archived] }
# 4. Enums
enum :status, { draft: "draft", published: "published", archived: "archived" }, default: :draft
# 5. Scopes
scope :recent, -> { order(created_at: :desc) }
scope :positioned, -> { order(:position) }
scope :active, -> { open.published.where.missing(:not_now) }
# 6. Delegations
delegate :name, to: :board, prefix: true, allow_nil: true
# 7. Callbacks (sparingly)
after_create_commit :broadcast_creation
# 8. Business logic methods
def publish
update!(status: :published)
track_event "card_published"
end
def move_to_column(new_column)
update!(column: new_column)
track_event "card_moved", particulars: {
from_column_id: column_id_before_last_save,
to_column_id: new_column.id
}
end
private
def broadcast_creation
broadcast_prepend_to board, :cards, target: "cards", partial: "cards/card"
end
end
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.
- 2d ago First seen · 297 lines · 78 tokens per session scan A 225b34a69625
model-patterns is a skill published in the GitHub repository dilolabs/nosia (212 stars, last pushed 24d ago), licensed MIT. It adds 78 tokens to every session and 1,938 once invoked, about $0.0004 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
debugging-output-and-previewing-html-using-ray
Use when user says "send to Ray," "show in Ray," "debug in Ray," "log to Ray," "display in Ray," or wants to visualize data, debug output, or show diagrams in the Ray desktop application.
fortify-development
ACTIVATE when the user works on authentication in Laravel. This includes login, registration, password reset, email verification, two-factor authentication (2FA/TOTP/QR codes/recovery codes), passkeys, profile updates, password confirmation, or any auth-related routes and controllers. Activate when the user mentions…
timeboxed-iterating
Use when the user specifies a task and a duration, and the work should be done iteratively by subagents over that time period.
project-snmp-profiles-authoring
Use when editing Netdata SNMP profile YAMLs, topology SNMP profiles, ddsnmp profile parsing, or profile-format documentation. Requires checking source MIB field accessibility, especially MAX-ACCESS not-accessible INDEX objects, before adding or changing profile symbols.
learn-pr-preview
Use only when the user explicitly asks to build, run, preview, inspect, or validate learn.netdata.cloud locally using the contents of a PR or documentation branch before merge. Do not trigger for ordinary docs edits unless the user asks for a local Learn preview.
add-custom-domain
Add a custom domain to a Temps project and provision an automatic SSL/TLS certificate via Let's Encrypt, driven entirely from the @temps-sdk/cli CLI. Handles subdomains, apex domains, HTTP-01 and DNS-01 challenges, and wildcard domains. Use when the user wants to: (1) Add a custom domain to their Temps app, (2) Set up…