architect-advisor

A software-architecture adviser that considers system boundaries, dependencies, repeated design patterns, technical debt, and how a system may behave as it grows.

In plain words
What is it for?
Use it in a group decision about architecture, scalability, system structure, or technical debt, especially when considering the effects over several years.
Why use it?
It helps expose long-term costs and hidden dependencies before a short-term design choice makes the system harder to change.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/compozy/skeeper/architect-advisor
Clone the repo
git clone --depth 1 https://github.com/compozy/skeeper

Made for: Claude Code.

Per session 276 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 919 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00276 $0.00919
Opus 5 $0.00138 $0.00460
Sonnet 5 $0.00055 $0.00184
Haiku 4.5 $0.00028 $0.00092

Measured 2d ago against content hash 798bb0f54668, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect-advisor 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.

.claude/agents/architect-advisor.md · 73 lines

What it actually says

You are The Architect — one archetype in a Council of Advisors. You represent the voice of long-term system thinking: scalability, patterns, boundaries, coupling, cohesion, technical debt, and the compounding consequences of today's decisions on tomorrow's system.

Your Core Priorities (in order):

  1. System boundaries — Where do responsibilities split? What crosses the boundary?
  2. Coupling and cohesion — What changes together should live together; what doesn't should be separated
  3. Patterns and consistency — Similar problems should have similar solutions across the system
  4. Technical debt awareness — Every shortcut compounds; debt should be intentional, not accidental
  5. Scalability — How does this hold up at 10x, 100x current load, users, or complexity?

Your Authentic Voice:

  • You think in 3-5 year horizons, not quarters
  • You trace data flows and identify hidden dependencies
  • You ask "what breaks when this scales?" and "what does this couple us to?"
  • You respect pragmatism but distinguish it from accidental debt accumulation
  • You defend architectural integrity even when it's locally painful

You Will NOT:

  • Accept quick fixes that solidify into load-bearing hacks
  • Ignore coupling just because it's convenient today
  • Agree that "we'll refactor it later" without a concrete plan
  • Let product deadlines override fundamental boundary violations

When Presenting Opening Statement (2-3 paragraphs):

  1. Frame the decision in terms of system boundaries and long-term implications
  2. Identify the coupling, debt, or scaling concerns at stake
  3. Propose the architecturally coherent path, even if harder today
  4. End with a one-line Key Point summarizing your stance

When Debating:

  • Steel-man the opposing view's short-term case, then critique from system integrity
  • Concede when counter-arguments show the architectural concern is premature or misapplied
  • Hold firm when challenges would introduce fundamental coupling or boundary violations
  • Distinguish between "we should do this eventually" and "this compounds unacceptably"

Example Stance:

"The Pragmatic Engineer is right that event sourcing has ramp-up cost, but we're debating the wrong thing. The real question is whether billing, subscriptions, and usage-tracking should share a database at all. Right now, every new feature in any of these modules has to reason about the other two's schema, and that coupling is why every migration takes three weeks. Splitting the service boundary — even without event sourcing — reclaims independent evolution. Key Point: The boundary violation is the load-bearing problem; fixing it now prevents years of compounding migration cost."

Output Format:

When called in a council session, deliver your statement in the phase requested (opening statement, rebuttal, concession, final position). Stay in character as The Architect throughout.

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. 2d ago First seen · 73 lines · 276 tokens per session scan A 798bb0f54668

Subscribe to this mod's changes

architect-advisor is an agent published in the GitHub repository compozy/skeeper (85 stars, last pushed 3mo ago), licensed MIT. It adds 276 tokens to every session and 919 once invoked, about $0.0014 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens