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 rules/vepo/issues/architecture-designgit clone --depth 1 https://github.com/vepo/issuesWhat 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 | $0.01292 | $0.01292 |
| Opus 5 | $0.00646 | $0.00646 |
| Sonnet 5 | $0.00258 | $0.00258 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
architecture-design 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture design (phase 2)
Part of the mandatory development-process.mdc. Every feature change that requires feature analysis also requires architecture design before task break. Do not write production or test code until phases 1–4 are complete for the current changelog entry.
Answering architecture questions (AQn) updates the feature doc only — it is not development approval. Each answer triggers a mandatory impact review — see development-process.mdc § Impact review when answering open questions.
Canonical references: ARCHITECTURE.md, issues-layered-architecture.mdc, issues-bounded-contexts.mdc.
When required
| Trigger | Architecture design required |
|---|---|
| Any change that triggers feature analysis (change-request-analysis.mdc § When required) | Yes — mandatory |
| Typo, comment-only, formatter, docs-only (no behaviour) | No — exempt with feature analysis |
No feature change skips architecture design. If feature analysis applies, architecture design applies.
Preconditions
- Phase 1 (feature analysis) exit criteria met for the changelog entry.
- Blocking feature questions (FQn) are
answeredornot valid. - Changelog Status:
planned(orarchitecture-readyif revisiting design after scope change).
Process
1. Add or extend ## Architecture on the feature doc
Document the technical design for the current changelog entry. Minimum areas:
| Area | Document |
|---|---|
| Bounded contexts | Which contexts participate; dependency direction (issues-bounded-contexts.mdc) |
| Packages / layers | Concrete packages; Endpoint → Service → Repository map per operation |
| API surface | Paths, HTTP verbs, Request/Response record names, auth roles |
| Schema / persistence | Tables, columns, FKs, indexes; Flyway baseline changes |
| Cross-context integration | CDI events, shared services — no repository calls across unrelated contexts |
| Frontend integration | Angular routes, services, API codegen impact |
| Tests | Endpoint tests, ArchUnit boundaries, Angular specs affected |
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 · 100 lines · 1,292 tokens per session scan A b96fc57a6235
architecture-design is a cursor rule published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,292 tokens to every session, about $0.0065 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.
Other cursor rules, from other repositories
external-scale
Source: docs/agents/external-scale.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
testing-visual
Source: docs/agents/testing-visual.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
integration-systems
Source: docs/agents/integration-systems.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
css-postcss
Source: docs/agents/css-postcss.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
nx-rules
// This file is automatically generated by Nx Console.
cursorrules
You are helping a developer work with Race Condition, an open-source multi-agent marathon simulation built with Google ADK and Gemini. It was demonstrated at the Google Cloud Next '26 Developer Keynote.