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 agents/lerianstudio/ring/backend-tsgit clone --depth 1 https://github.com/LerianStudio/ringWhat 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 | $0.00043 | $0.01837 |
| Opus 5 | $0.00022 | $0.00919 |
| Sonnet 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 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 — 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.
- 2d 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 (210 stars, last pushed 13d 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. 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
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.
geo-schema-render
Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.
implementer
Executes a single plan task using TDD. Writes tests first, then production code, then refactors. Reports status with evidence.
company-finder
Discovery-mode agent. Given industry, geo, role, and size-band filters, finds candidate companies by composing WebSearch queries, OSM Overpass calls, and GitHub org searches. Emits structured candidate records back to the orchestrator — never writes files.
lead-validator
Blind validator agent. Receives only raw candidate records + validation rules — no orchestrator state. Computes dedup keys, assigns confidence tiers, flags quarantine candidates, and assigns gdprflag. Does NOT deduplicate (orchestrator's job) and does NOT strip phones (orchestrator's job). Never writes files.