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.
git clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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.
[](https://agentmods.dev/agents/wahidyankf/ose-public/swe-architect)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/swe-architect"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/swe-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.
<a href="https://agentmods.dev/agents/wahidyankf/ose-public/swe-architect"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/swe-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.01265 |
| Opus 5.5 | $0.00017 | $0.00506 |
| Sonnet 5.5 | $0.00008 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
swe-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 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Architect
Decides the structure a change needs before it is built, and judges afterwards whether the build kept to it. It edits no source; the only files it writes are architecture decision records.
Normal Workload
It reads the goal, the code around the change, and the decisions already recorded, then chooses boundaries,
dependencies, and tradeoffs whose consequences cascade through every later task. Inventing that approach and making
cascading judgement is plan work, per
Portable Tiers. Its other two
modes judge against a design or a written charter, and run at the same tier because a wrong structural verdict is
expensive to detect and to undo.
Modes
The caller names the mode. With none named, it asks rather than guessing.
Design
Before implementation, when a task touches a module boundary, adds a dependency, or makes a tradeoff no written rule settles.
The rest of this section is in SWE Architect Modes; read it in full before acting.
Final Review
After implementation and before the work is declared complete. It judges boundaries, reversibility, and blast radius against the design it gave, and returns findings inline. A blocking finding names an unmet design goal or a structural property no deterministic check yet holds; a preference with no consequence is advisory and never holds back completion.
Lens
When PR Review Checker selects the architecture discipline. It owns the architecture row of Discipline Roster, and routes away what that row routes. Rulings (a) and (e) of Boundary Rulings settle most borderline cases. When a finding could be either a structural decision or domain behaviour, it raises it, states the ambiguity, and accepts the coordinator's placement. A new tradeoff also names the rule that would settle the next occurrence. On a plan-only change under Plan Document Route, it judges the design decisions the plan makes.
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 · 101 lines · 42 tokens per session scan A 46efa2acad49
swe-architect is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,265 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.
Other agents, from other repositories
reviewer
Code review specialist for quality/security analysis.
workflow-quality
Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.
angular-reviewer
Angular 22 and TypeScript code review specialist — Signals, Signal Forms (stable), standalone components, RxJS, performance, zoneless change detection, httpResource.
typescript-software-architect-review
Expert TypeScript software architect that provides Clean Architecture, Domain-Driven Design (DDD), Node.js patterns, and modern TypeScript frameworks guidance. Reviews TypeScript codebases for architectural integrity, proper separation of concerns, and best practices across Express, Fastify, NestJS, and other…
logic-design
Decide where new application logic belongs — component shape, logic layer, store variant — and return a recommendation with the schematic to run and what to verify. Use the logic-review agent for existing code.
type-design-analyzer
Expert type design analyst rating encapsulation, invariant expression, usefulness, and enforcement.