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/ag0os/rails-dev-plugin/rails-stack-profilesnpx skills add ag0os/rails-dev-plugin --skill rails-stack-profilesgit clone --depth 1 https://github.com/ag0os/rails-dev-pluginWhat 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 | $0.00092 | $0.01227 |
| Opus 5 | $0.00046 | $0.00613 |
| Sonnet 5 | $0.00018 | $0.00245 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
rails-stack-profiles 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rails Stack Axes
Resolve a project's architecture once per session, as two independent binary axes. Other skills consume the resolved axes to load one flat, branch-free guidance file each — they never carry inline omakase / service-oriented conditionals.
See axis-a.md and axis-b.md for characteristic patterns and code per axis value.
The Two Axes
A project is not one of three profiles. It is one value on each of two axes:
| Axis | Values | Question it answers |
|---|---|---|
| A — logic placement | native | extracted |
Where does non-trivial business logic live? |
| B — delivery | html | api |
Does the surface render HTML or serve JSON? |
native— logic lives in models, concerns, and POROs. The Rails-omakase way. Callbacks are acceptable for simple side effects.extracted— service/command objects are the default home for non-trivial logic. Common in larger teams and complex domains.html— server-rendered views, Hotwire (Turbo + Stimulus).api— headless JSON, serializers, noapp/views/(mailer views aside).
The axes are independent. All four combinations are valid, including native + api (a Rails 8 omakase-style API-only app — a combination the old three-profile enum could not express).
The legacy names map cleanly: omakase = native + html, service-oriented = extracted + html, api-first = extracted + api.
What is NOT an axis
Test framework, test data strategy, job backend, cache store, and auth library are orthogonal project facts, not architecture axes. A project with extracted services can still use Minitest; an omakase app can run Sidekiq. Inferring these from architecture is the central mistake this restructure removes.
Detect them directly via the project-conventions fingerprint. Skills consume those fingerprint fields; they never branch on a "profile" for them.
Detecting Axis A — logic placement
| Signal | Points to |
|---|---|
app/services/ with ~5+ files |
extracted |
Custom ApplicationService / BaseService base class |
extracted |
gem "dry-monads", gem "interactor", gem "trailblazer" |
extracted |
app/services/ absent or near-empty |
native |
Domain logic in models + app/models/concerns/ |
native |
| Callbacks orchestrating multi-step workflows | native |
POROs for operations, often in app/models/ |
native |
What ships with it
2 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.
- 2d ago First seen · 94 lines · 92 tokens per session scan A b1b751de9dcc
rails-stack-profiles is a skill published in the GitHub repository ag0os/rails-dev-plugin (5 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 1,227 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.