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 skills add kouroshez/coding-os --skill railsgit clone --depth 1 https://github.com/kouroshez/coding-osWrote 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/kouroshez/coding-os/rails)<a href="https://agentmods.dev/skills/kouroshez/coding-os/rails"><img src="https://agentmods.dev/badge/skills/kouroshez/coding-os/rails/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.
<a href="https://agentmods.dev/skills/kouroshez/coding-os/rails"><img src="https://agentmods.dev/badge/skills/kouroshez/coding-os/rails.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00100 | $0.00807 |
| Opus 5 | $0.00050 | $0.00404 |
| Sonnet 5 | $0.00020 | $0.00161 |
| Haiku 4.5 | $0.00010 | $0.00081 |
Grade A, and why
rails 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 5d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REQUIRED BACKGROUND: This skill depends_on: [clean-code, backend-fundamentals]. clean-code gives universal code quality (fail-closed errors, typed exceptions, self-documenting code, error-path tests); backend-fundamentals gives stack-agnostic backend patterns (services, idempotency, envelopes, N+1, migrations, auth). This skill adds ONLY Ruby on Rails-specific layering on top.
rails
Layer contract (matches structure.tree)
| Layer | May import | Never |
|---|---|---|
config/routes.rb |
route helpers | controller bodies, models |
*_controller.rb |
the domain model, concerns | another controller, raw SQL |
app/models/*.rb (ActiveRecord) |
other models, the DB | controllers, params, render |
controllers/concerns/ |
models (for auth lookups) | a specific controller's privates |
Controllers stay thin and transport-aware; models stay transport-free (no
params, no render) so they are unit-testable and the business logic survives
a transport swap (REST → GraphQL → ActionCable).
Routes & controllers (thin)
config/routes.rbis the single routing table — preferresources/resourceover hand-rolledmatch; one URL, one place.- An action: strong-parameter the input (
params.require(:x).permit(:a, :b)) → call ONE model method →render. No business branching, no multi-query loops. - Subclass
ApplicationController; never rescue-and-shape inside an action — raise a typed error and let the global chain map it. before_actionfilters load records / enforce auth; keep them in concerns when three controllers share them (rule of three), not copy-pasted.
Models (ActiveRecord — the only layer that thinks)
- Business logic, scopes, and
validateslive on the model; a controller that validates by hand is a layering violation. - Persist with
save!/create!/update!so a failure raises and therescue_fromchain maps it — silentsavethat returnsfalsehides errors. - Migrations are reversible (
change, or pairedup/down); schema and data migrations stay in separate files. The agent writes them; the user runsdb:migrate.
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.
- 5d ago First seen · 63 lines · 100 tokens per session scan A ac894a14deaf
rails is a skill published in the GitHub repository kouroshez/coding-os (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 100 tokens to every session and 807 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
booboo-adapter
Feed data into a Booboo brain that the built-in postgres and json adapters do not cover — write a small config-driven adapter against the spec instead of forking the builder. Use when a source is Neo4j, an API, a CSV export, a proprietary store, or any shape the standard config cannot express.
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
potpie-infra-architecture
Use for project infra and architecture context: environments, adapters, runtime configuration, deployments, service dependencies, datastores, API contracts, ownership, incidents, and dependency blast radius.
potpie-project-preferences
Use before writing, modifying, reviewing, refactoring, or testing code so repo/project preferences surface: error handling, file structure, frameworks, logging, dependency choices, testing, security, API style, and naming. Also use after code work when a reusable project preference should be recorded.
supabase-node
Express/Hono with Supabase and Drizzle ORM.
solr-extending
To build Solr plugins: SearchComponent, QParser, URP, DocTransformer.