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 sorah/config --skill rails-protobufgit clone --depth 1 https://github.com/sorah/configWrote 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/sorah/config/rails-protobuf)<a href="https://agentmods.dev/skills/sorah/config/rails-protobuf"><img src="https://agentmods.dev/badge/skills/sorah/config/rails-protobuf/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/sorah/config/rails-protobuf"><img src="https://agentmods.dev/badge/skills/sorah/config/rails-protobuf.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 | $0.00205 | $0.03109 |
| Opus 5.5 | $0.00082 | $0.01244 |
| Sonnet 5.5 | $0.00041 | $0.00622 |
| Haiku 4.5 | $0.00020 | $0.00311 |
Grade A, and why
rails-protobuf 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 yesterday.
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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protobuf-native Rails
Conventions for a Rails app whose .proto files are the schema of record: requests, responses, errors and structured columns are generated messages, never Hash literals. The stack:
- connect_rpc_rails: Connect unary RPCs as
ActionController::APIactions, routed from the service descriptor. - protobufable:
protobuf_bodyrequest bodies,render proto_json:, Alba resources bound to messages, messages in columns, a problem catalogue in a protobuf enum, and Connect error rendering for problems. - protovalidate:
buf.validaterules on requests and columns. - problem: RFC 9457 errors. Read /sorah-guides:rails-problem for the error model itself.
Examples come from ruby-no-kai/sponsor-app (docs/protobuf.md there is the long-form tour). Project-specific conventions (CLAUDE.md, docs/) always take priority. For Sorbet details read /sorah-guides:sorbet; the protobuf-specific gaps are in references/limits.md.
Layout and generation
| Concern | Where |
|---|---|
| Schema | proto/<org>/<app>/*.proto, a buf module, one package, option ruby_package set |
| Generated Ruby + RBS | gen/proto/ruby/ as a path gem the Gemfile loads |
| Generated TypeScript | ui/src/gen/ (protoc-gen-es) |
| Connect controllers | app/controllers/api/<service>/ |
| Response builders | app/resources/api/ (Alba) |
| Problem catalogue | proto/.../problem.proto, app/models/errors.rb |
| Storage messages | proto/.../internal/, never reachable from a service |
- One task regenerates everything (
mise run gen:buf build,buf generateper template, thentapioca dsl --only=Protobuf). Generated files are committed; CI reruns generation and fails on a dirty tree. Regenerate after every.protoedit, comment-only ones included, since comments become JSDoc. buf buildruns first so a.protothat does not compile leavesgen/untouched.- Message classes cannot reload (a duplicate descriptor raises), so they load once through Bundler and the dev server restarts when
gen/changes. Do not put_pb.rbunder Zeitwerk. - Vendored
.protofrom a gem (proto/protobufable/) is excluded from Ruby generation, as the gem ships its own Ruby; a second copy of a descriptor fails boot. Guard the vendored copy with a spec comparing it to the gem's. - Proto doc comments are user-facing documentation. Write them for API clients.
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.
- yesterday First seen · 207 lines · 205 tokens per session scan A c8f48a5a23c1
rails-protobuf is a skill published in the GitHub repository sorah/config (31 stars, last pushed yesterday), licensed MIT. It adds 205 tokens to every session and 3,109 once invoked, about $0.0008 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 2026-10-17.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.