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/vypdev/copilotWrote 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/rules/vypdev/copilot/architecture)<a href="https://agentmods.dev/rules/vypdev/copilot/architecture"><img src="https://agentmods.dev/badge/rules/vypdev/copilot/architecture/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/rules/vypdev/copilot/architecture"><img src="https://agentmods.dev/badge/rules/vypdev/copilot/architecture.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 | $0.00308 | $0.00308 |
| Opus 5.5 | $0.00123 | $0.00123 |
| Sonnet 5.5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
architecture 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 1mo 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.
What it actually says
Architecture and key paths
Use _agent/docs/architecture.md as the concise repository map and
docs/development/architecture.mdx plus docs/dependency-rules.md as the
authoritative architecture contract. Do not duplicate an older source tree or
action catalog in this rule.
The dependency direction is:
entrypoint
-> lifecycle/composition root
-> application use case/workflow
-> semantic application port
-> specialized adapter
-> provider client/detail
Current source roots:
src/actions/: GitHub and local runtime boundaries.src/application/usecases/: orchestration and workflows.src/application/policies/: deterministic application decisions.src/application/ports/: semantic capability contracts.src/data/model/andsrc/domain/: provider-neutral core.src/data/repository/: specialized external adapters.src/infrastructure/github/: Octokit and GraphQL transports.src/infrastructure/composition/: the only dependency assembly layer.
Release and hotfix deployment use the durable orchestration state machine. The
canonical callback actions are declared in src/data/model/action_types.ts;
there is no second deployment or branch-merge implementation.
Before changing a boundary, inspect the current source and run the architecture tests. Graphify output is a navigation aid, not an architecture authority.
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.
- 1mo ago Changed · -30 lines · -1,174 tokens per session 6a64546b0a4b
- 1mo ago Changed · +18 tokens per session ca6d29bd8488
- 1mo ago First seen · 71 lines · 1,464 tokens per session scan A 3b2d879ce1f2
architecture is a cursor rule published in the GitHub repository vypdev/copilot (3 stars, last pushed today), licensed MIT. It adds 308 tokens to every session, about $0.0012 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 2026-08-31.
Other cursor rules, from other repositories
code-review-en
Code Review Guidelines (English).
task-summary
Enforce Summary and Session Log blocks on every coding response when session tracking is enabled.
api-steps
How to create HTTP endpoints in Motia.
virtual-steps
Connecting nodes virtually and creating a smooth flow in Workbench.
201-bugbot-autofix
200: Responding to BugBot PR comments.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.