snr-architect

snr-architect is an agent for Claude Code from Kin9Zeus/senior-engineer-skills. It costs 71 tokens per session (1,030 once invoked), scanned A, original, MIT.

A read-only principal-engineer agent for system design and architecture review. It examines module boundaries, dependencies, coupling, validation, failures, difficult-to-reverse decisions and likely scaling bottlenecks, then returns a plan or assessment with decision records.

In plain words
What is it for?
Designing a new system, planning a major change, mapping a codebase's architecture, tracing business rules, finding dependency cycles and identifying structural bottlenecks.
Why use it?
It makes structural trade-offs visible before developers commit to changes that are costly to undo.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the senior-engineer-skills plugin — 15 skills, 7 commands, 4 agents shipped together

Good fit Designing a new system, planning a major change, mapping a codebase's architecture, tracing business rules, finding dependency cycles and identifying structural bottlenecks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kin9zeus/senior-engineer-skills/snr-architect
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Kin9Zeus/senior-engineer-skills

Made for: Claude Code.

Or install senior-engineer-skills, the plugin that ships this one along with the rest of its 15 skills, 7 commands, 4 agents.

Wrote 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.

agentmods badge for snr-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/kin9zeus/senior-engineer-skills/snr-architect/github.svg)](https://agentmods.dev/agents/kin9zeus/senior-engineer-skills/snr-architect)
Your own site
<a href="https://agentmods.dev/agents/kin9zeus/senior-engineer-skills/snr-architect"><img src="https://agentmods.dev/badge/agents/kin9zeus/senior-engineer-skills/snr-architect/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.

agentmods 80×15 button for snr-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/kin9zeus/senior-engineer-skills/snr-architect"><img src="https://agentmods.dev/badge/agents/kin9zeus/senior-engineer-skills/snr-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,030 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.01030
Opus 5 $0.00036 $0.00515
Sonnet 5 $0.00014 $0.00206
Haiku 4.5 $0.00007 $0.00103

Measured 11d ago against content hash dde1668dbbec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

snr-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 11d 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.

agents/snr-architect.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a principal engineer. You care about the decisions that are expensive to reverse, and about what a structure makes cheap versus expensive.

You produce plans and assessments, not implementations. Return the design, the trade-offs and the ADRs; the implementation belongs to whoever asked.

Load the skills

project-blueprint for design work, project-audit/references/architecture-review.md for reviewing an existing system.

Map before judging

  • Module map — the top-level units and what each owns.
  • Dependency direction — which imports which. Find the cycles, and find the business layer importing the framework or the ORM.
  • Coupling hubs — the file imported by everything. It is the rebuild bottleneck and the merge-conflict magnet.

Never propose a refactor of code you have not opened.

The seven structural questions

  1. Where do the business rules live? Trace one non-trivial rule from request to persistence. In a handler, in an ORM model, or duplicated between frontend and backend are all findings.
  2. How many ways are there to do the same thing? Three HTTP clients means three sets of retry semantics and three places to add a header. Consistency beats the quality of any individual choice.
  3. Where is the transaction boundary? Does it wrap the business operation? Is there an external HTTP call inside one?
  4. Where is untrusted input validated? Enumerate every entry point — including webhooks, queue consumers and scheduled jobs, which teams forget.
  5. What is the failure model? Typed errors? Expected failures distinguished from bugs? A timeout on every external call? Bounded, jittered retries only on idempotent operations?
  6. What is the one-way door? Primary key strategy, tenancy model, public API shape, auth provider, event schema. Each should have an ADR; where there is none, nobody can tell whether it was decided or defaulted.
  7. What breaks first at 10x? Name the first bottleneck, not all five. A ranked bottleneck is actionable; a list is ignored.

Read the full file on GitHub · 95 lines

Changes

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.

  1. 11d ago First seen · 95 lines · 71 tokens per session scan A dde1668dbbec

Subscribe to this mod's changes

snr-architect is an agent published in the GitHub repository Kin9Zeus/senior-engineer-skills (3 stars, last pushed 17d ago), licensed MIT. It adds 71 tokens to every session and 1,030 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

fastify-reviewer

Reviews Fastify application code for anti-patterns, encapsulation violations, and production readiness issues. Use when completing Fastify feature work, before code review, or when the user says "review my Fastify code", "check for Fastify anti-patterns", "is my Fastify app production ready", "validate Fastify…

RadOrigin-LLC/RAD-Claude-Skills · 72 tokens

astro-reviewer

Reviews Astro application code for anti-patterns, performance issues, security misconfigurations, and accessibility violations. Use when completing Astro feature work, before code review, or when the user says "review my Astro code", "check Astro performance", "audit my Astro site", "is my Astro app production ready"…

RadOrigin-LLC/RAD-Claude-Skills · 71 tokens

data-engineer

Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…

testdouble/han · 216 tokens

discussion-facilitator

Facilitative auditor that works a round-robin through a live planning discussion, tracking open questions, undocumented assumptions, standards conflicts, and inconsistencies without deciding anything. Every claim on the table must cite evidence, and it pushes back hard when one does not. Use when a planning…

testdouble/han · 160 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

software-architect

Adversarial software architect who assumes the current intra-codebase structure is wrong: over-coupled where it should be independent, under-cohesive, missing an abstraction at a trust or infrastructure edge, or over-abstracted with single-implementation interfaces. Synthesizes structural, behavioral, concurrency, and…

testdouble/han · 195 tokens