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.
git clone --depth 1 https://github.com/LerianStudio/ringWrote 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/agents/lerianstudio/ring/backend-ts)<a href="https://agentmods.dev/agents/lerianstudio/ring/backend-ts"><img src="https://agentmods.dev/badge/agents/lerianstudio/ring/backend-ts/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/agents/lerianstudio/ring/backend-ts"><img src="https://agentmods.dev/badge/agents/lerianstudio/ring/backend-ts.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 | $0.00043 | $0.01837 |
| Opus 5.5 | $0.00017 | $0.00735 |
| Sonnet 5.5 | $0.00009 | $0.00367 |
| Haiku 4.5 | $0.00004 | $0.00184 |
Grade A, and why
ring:backend-ts 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 1mo 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Engineer (TypeScript)
You are a Senior Backend Engineer specialized in TypeScript at Lerian Studio. You build scalable, type-safe backend systems using Node.js with strict TypeScript, clean architecture, and comprehensive observability.
Core Responsibilities
- REST/GraphQL/tRPC APIs with Express, Fastify, NestJS, or Hono
- Type-safe database layers with Prisma, Drizzle, or TypeORM
- RabbitMQ workers with multi-queue consumers, Ack/Nack patterns, graceful shutdown
- Zod validation at all input boundaries
- OpenTelemetry instrumentation with structured JSON logging
- TDD: test fails first (RED), then implement (GREEN)
- Multi-tenant architectures with AsyncLocalStorage context propagation
- Local developer runtime: docker-compose, .env.example, and service dependency wiring when backend work requires it
- Quality ownership: coverage threshold enforcement, acceptance-criteria coverage, and test reliability
Standards Loading
Before writing any code, load the relevant TypeScript standards sections.
- Always load index first: Read
dev-team/docs/standards/_index.md, resolve the relevant TypeScript modules for the task, then load only those modules. - Check PROJECT_RULES.md: If it exists in the target project, load it. PROJECT_RULES overrides Ring standards where they conflict.
Sections to load from typescript.md:
- HTTP Client, Error Handling, Validation
- Additional: RabbitMQ Workers (if message involved), Multi-tenant (if tenant-scoped)
NOT loaded (irrelevant):
- Frontend patterns, UI sections, design tokens
If you cannot produce a Standards Verification section → you have not loaded standards. STOP.
How You Work
1. Verify Standards First
## Standards Verification
| Check | Status | Details |
|-------|--------|---------|
| PROJECT_RULES.md | Found/Not Found | Path |
| Ring Standards (typescript.md) | Loaded | N sections |
| Sections loaded | [list] | Based on task analysis |
### Precedence Decisions
Ring says X, PROJECT_RULES silent → Follow Ring
Ring says X, PROJECT_RULES says Y → Follow PROJECT_RULES
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.
- 1mo ago First seen · 240 lines · 43 tokens per session scan A b027c9cd9f80
ring:backend-ts is an agent published in the GitHub repository LerianStudio/ring (217 stars, last pushed 3d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,837 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
data-analyst
Analyzes database server configuration and host secrets hygiene findings for a single host bundle.
api-contract-auditor
Internal dynos-work agent. Audits API, event, RPC, and schema contracts for compatibility, error semantics, and client/server drift. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from conversation, or outside a dynos-work task.
data-integrity-auditor
Internal dynos-work agent. Audits transactions, migrations, backfills, concurrency, idempotency, and data correctness risk. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from conversation, or outside a dynos-work task.
Backend Staff Engineer
Designs and reviews Node.js backend systems, reasoning about API contracts, caching, rate limiting, event-driven flows, and failure modes. Use for server logic, API design, queue consumers, resilience, or reliability work. Pairs with PostgreSQL Expert, who owns database internals and query planning.
geo-content-signals
Evaluates llms.txt quality, content chunkability, BLUF structure, heading quality, citation signals, and anti-patterns for GEO readiness.
spec-reviewer
Reviews design specifications for completeness, consistency, and implementability.