architecture-vault

A repository rulebook that records which codebase is the official source and how related SDK files and API settings must stay aligned. A monorepo is one repository containing multiple projects; a git subtree mirror is a copied project kept in sync from another repository.

In plain words
What is it for?
Use it when changing the Kimss Python SDK, choosing API hosts or authentication, checking deprecated routes, or updating SDK coverage and context documentation.
Why use it?
It prevents developers from editing the wrong copy or letting related documentation and API details drift apart.

Cursor rule for Cursor

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 rules/kimss-ai/kimss-python-sdk/architecture-vault
Clone the repo
git clone --depth 1 https://github.com/kimss-ai/kimss-python-sdk

Made for: Cursor.

Per session 292 This file is loaded in full into every session.
When invoked 292 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00292 $0.00292
Opus 5 $0.00146 $0.00146
Sonnet 5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured today against content hash cbccf07fbf5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architecture-vault 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 today.

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.

.cursor/rules/architecture-vault.mdc · 19 lines

What it actually says

Kimss SDK — mirror and coverage

Source of truth: this directory lives under private monorepo kimssApi/kimss_sdk/. The public kimss-python-sdk repo is a git subtree force-push mirror. Never treat the public main as an editable SSOT.

Cross-repo notes (local): C:\projects\kimss-docsarchitecture/sdk-overview.md, api/sdk-coverage.md.

Conventions

  • Prefer OpenAI gateway: base_url=https://api.kimss.ai/v1 + X-Kimss-Agent-Id (see AI_INTEGRATION.md).
  • client.agents.run / chat / models.create are deprecated for inference.
  • Public SDK param name: conversation_id (v2) on residual agent APIs.
  • Canonical host: https://api.kimss.ai. Auth: X-Kimss-Key or Bearer on /v1.
  • Dense HTTP map in-package: docs/llm-context.md.
  • Platform/DB/backoffice architecture is not this package’s job — use kimss-docs / kimssApi cursor_application_docs/.

When changing client routes

Update vault api/sdk-coverage.md and keep docs/llm-context.md in sync in the same monorepo change.

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. today First seen · 19 lines · 292 tokens per session scan A cbccf07fbf5a

Subscribe to this mod's changes

architecture-vault is a cursor rule published in the GitHub repository kimss-ai/kimss-python-sdk (1 stars, last pushed 2d ago), licensed MIT. It adds 292 tokens to every session, about $0.0015 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.