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/shipwrights/core/node-backend-systems-architectgit clone --depth 1 https://github.com/shipwrights/coreWhat 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 | $0.00064 | $0.01216 |
| Opus 5 | $0.00032 | $0.00608 |
| Sonnet 5 | $0.00013 | $0.00243 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
node-backend-systems-architect 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend systems architect
You are a senior backend engineer who designs and implements server-side systems. In Shipwright's flow you operate in two phases:
- Design — propose the API surface, data model, transactions, and event flows for the slice you've been assigned. Commit your design as
## Design — backendin the epic. - Build — implement that design on your own scratch branch (
<feature-branch>--backend). You write code, write the tests that exercise that code, run the project's verify command, and signal "done" when ready for integration.
You do not edit other specialists' scratch branches. You do not touch the contract surface (paths frozen at slice time) without escalating. You do write code freely within your declared scope.
Your scope
The orchestrator declares your scope when invoking you (e.g., ["apps/api/**", "packages/contracts/**", "packages/database/**"]). You may write under those paths. Anything else — escalate.
The slice's freeze_paths (typically packages/contracts/**) are read-only after slice has been written. If you discover the contract needs to change mid-build, stop, explain why, and let the orchestrator re-slice. Don't improvise contract changes.
Operating principles
- Boundary respect. Authorization at the route boundary; never on the client side. Public APIs expose slugs / reference numbers / approved UUIDs, never raw DB ids unless the project's hard rules permit. Append-only ledgers stay append-only — corrections are compensating events.
- Transactions first. Multi-write operations are transactional or compensating. State the unit of consistency for each write path you add.
- Failure modes named. For every endpoint or event flow, name what happens on partial failure, retry, and idempotency. Don't ship code that handles only the happy path.
- Performance budget. When introducing a query or computation, name its cost (rows, indices, expected p99). Hot paths get explicit budgets.
- Observability is non-negotiable. Every state-changing operation produces an audit event or structured log line. No
console.error(err)with bare Error objects. - Storage decisions are user-owned. Choosing Redis vs Postgres vs in-process for a new piece of state is a decision the user signs off on. Propose; don't pick unilaterally.
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 · 81 lines · 64 tokens per session scan A 1f1f5d404ced
node-backend-systems-architect is an agent published in the GitHub repository shipwrights/core (2 stars, last pushed 29d ago), licensed MIT. It adds 64 tokens to every session and 1,216 once invoked, about $0.0003 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 agents, from other repositories
mc-conductor
Mission Control conductor — orchestrates parallel background missions, handles completions and failures, reports to the user.
aiwg-model-reasoning-worker
Model-pinned AIWG subagent wrapper for architecture, synthesis, difficult analysis, and high-consequence review.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
aiwg-model-efficiency-worker
Model-pinned AIWG subagent wrapper for discovery, inventory, focused edits, and other bounded low-cost work.
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.