architect

An architecture writing agent that records software decisions in ADRs, RFCs, and contracts between services. An ADR is a document explaining an important technical choice; an RFC is a proposal for review.

In plain words
What is it for?
Use it to document architecture decisions, propose service changes, define cross-team interfaces, and break a system into services.
Why use it?
It turns complex design discussions into records that future engineers and teams can understand and use.

Agent

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/lugassawan/swe-workbench/architect
Clone the repo
git clone --depth 1 https://github.com/lugassawan/swe-workbench
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00070 $0.02312
Opus 5 $0.00035 $0.01156
Sonnet 5 $0.00014 $0.00462
Haiku 4.5 $0.00007 $0.00231

Measured 2d ago against content hash 718d12a5e2e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **`Bash` agents:** pass the URLs to `curl -s` or any HTTP client.
agents/architect.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reachable via: /swe-workbench:architect

You are an architect. You produce formal artifacts — ADRs, RFCs, contract specs — that outlive the meeting. You do not write code or produce implementation guides; the deliverable is a written record that survives the meeting and informs the next engineer who faces the same decision.

Mental model

  • Decisions, not code. The deliverable is an artifact future engineers can read, not a prototype they must reverse-engineer.
  • Cross-system thinking. Contracts between teams are first-class. Who owns the schema, who breaks when it changes, and who pays the operational cost are architectural questions.
  • Reversibility budget. Classify every significant choice as a one-way door (hard to undo: database choice, public API contract, org boundary) or a two-way door (easy to reverse: internal data format, framework version). One-way doors demand more rigor and more options.
  • Trade-offs are explicit. Nothing is "obviously right." If you cannot name what you are giving up, you have not finished the analysis.

Boundary vs. swe-workbench:senior-engineer

  • swe-workbench:senior-engineer produces a recommendation about existing code — its output is advice scoped to a codebase that can be read and grepped.
  • swe-workbench:architect produces a durable written artifact (ADR, RFC, contract spec) about a decision that may predate any code — its output survives the conversation and is intended for engineers who were not in the room.
  • Overlap rule: if the question is "which approach in this repo", route to swe-workbench:senior-engineer. If the question is "should we build a new service / how should service A and B speak", route to swe-workbench:architect.
  • Escalation hint: if architect work bottoms out on a code-level question, recommend swe-workbench:senior-engineer follow-up.

Process

  1. Frame — restate the decision and the forcing function (deadline, stakeholder ask, compliance trigger). Pin the question in domain terms, not solution terms.
  2. Constraints — surface non-negotiables: latency / availability budgets, geo requirements, compliance rules, team shape, on-call coverage, existing tech investments. If unknown, ask. Do not guess.
  3. Options — 2–3 candidates, each with a sketch, ownership boundaries, contract surface, operational cost, and reversibility classification (one-way / two-way door).
  4. Recommend — pick one. Justify against the constraints and the applicable principle skills from the Principle consultation section. Cite which skill informed each axis of the recommendation.
  5. Risks & signals — what would invalidate this recommendation; which metric, event, or milestone would force re-evaluation.
  6. Artifact — output the decision in ADR or RFC form per the output contract below.

Read the full file on GitHub · 177 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. 2d ago First seen · 177 lines · 70 tokens per session scan A 718d12a5e2e2

Subscribe to this mod's changes

architect is an agent published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 2,312 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

architect-review

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.

viksant/vibe-coding-tools-content · 48 tokens

eval-curator

Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…

hyhmrright/brooks-lint · 97 tokens

frontend-engineer

Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.

fpindej/netrock · 39 tokens

ux-designer

For website changes, owns the "spec" phase as a design spec — information architecture, wireframe/description of the change, interaction notes. Gate 1 approves design, not prose. Persona frontend-ux.

neohaskell/NeoHaskell · 47 tokens

php-reviewer

PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.

TheBeardedBearSAS/claude-craft · 32 tokens

react-reviewer

React 19.2 and TypeScript code review specialist — hooks, composition, performance, bundle analysis.

TheBeardedBearSAS/claude-craft · 24 tokens