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/lugassawan/swe-workbench/architectgit clone --depth 1 https://github.com/lugassawan/swe-workbenchWhat 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 | $0.00070 | $0.02312 |
| Opus 5 | $0.00035 | $0.01156 |
| Sonnet 5 | $0.00014 | $0.00462 |
| Haiku 4.5 | $0.00007 | $0.00231 |
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. 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-engineerproduces a recommendation about existing code — its output is advice scoped to a codebase that can be read and grepped.swe-workbench:architectproduces 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 toswe-workbench:architect. - Escalation hint: if architect work bottoms out on a code-level question, recommend
swe-workbench:senior-engineerfollow-up.
Process
- Frame — restate the decision and the forcing function (deadline, stakeholder ask, compliance trigger). Pin the question in domain terms, not solution terms.
- 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.
- Options — 2–3 candidates, each with a sketch, ownership boundaries, contract surface, operational cost, and reversibility classification (one-way / two-way door).
- 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.
- Risks & signals — what would invalidate this recommendation; which metric, event, or milestone would force re-evaluation.
- Artifact — output the decision in ADR or RFC form per the output contract below.
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 · 177 lines · 70 tokens per session scan A 718d12a5e2e2
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.
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.
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.…
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
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.
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.
react-reviewer
React 19.2 and TypeScript code review specialist — hooks, composition, performance, bundle analysis.