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/kimss-ai/kimss-python-sdkWrote 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/kimss-ai/kimss-python-sdk/kimss-product)<a href="https://agentmods.dev/rules/kimss-ai/kimss-python-sdk/kimss-product"><img src="https://agentmods.dev/badge/rules/kimss-ai/kimss-python-sdk/kimss-product/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/kimss-ai/kimss-python-sdk/kimss-product"><img src="https://agentmods.dev/badge/rules/kimss-ai/kimss-python-sdk/kimss-product.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 | $0.00022 | $0.00523 |
| Opus 5.5 | $0.00009 | $0.00209 |
| Sonnet 5.5 | $0.00004 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
kimss-product 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 2mo 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
Kimss — product integration (public)
What Kimss is
Kimss is a Secure AI Gateway and Governance Control Plane for autonomous agents (identity, audit trail, kill switch, provider vault). It does not host inference. Integrations should keep the native OpenAI or Anthropic SDK and point it at the dual-listener gateway, not custom chat wrappers.
Canonical hosts
- Gateway (OpenAI):
https://api.kimss.ai/v1 - Gateway (Anthropic):
https://api.kimss.ai(SDK appends/v1/messages) - Control-plane API root:
https://api.kimss.ai(no trailing slash) - Staging:
https://stg.kimss.ai
Authentication
- Gateway / OpenAI or Anthropic clients:
api_key=kimss_...(Bearer orx-api-key) plusX-Kimss-Agent-Id(required for attribution / JIT discovery / kill switch). - Control-plane
KimssClient/ MCP: HTTP headerX-Kimss-Key. Env:KIMSS_WORKSPACE_KEYorKIMSS_API_KEY. - Never commit keys; never log key values.
Conventions
- Preferred inference: keep the native SDK. OpenAI →
base_url="https://api.kimss.ai/v1"(POST /v1/chat/completions). Anthropic →base_url="https://api.kimss.ai"(POST /v1/messages). - Deprecated:
KimssClient.agents.run,chat,Agent.query,models.create, MCPkimss_chat/kimss_run_agent/kimss_complete. - Control plane:
agents.register,usage.report; kill switchPOST /agent_set_status/; auditPOST /audit_log/. - Azure official clients are not inbound drop-ins. Vault Azure (and any backend) under Provider Vault.
Dense context
- AI_INTEGRATION.md — mandatory A2A rules.
- docs/KIMSS_ONBOARDING.md
- docs/llm-context.md and .llms.txt
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.
- 2mo ago First seen · 37 lines · 22 tokens per session scan A 9d59860a56b5
kimss-product is a cursor rule published in the GitHub repository kimss-ai/kimss-python-sdk (1 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 523 once invoked, about $0.0001 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
plugin-development
Plugin Development Standards - Applies to all new wasm and golang-filter plugins.
windsurfrules
Create detailed components with these requirements.
reachai-project
ReachAI project rules for AI coding agents.
selectools-providers
Rules for working with LLM provider adapters in selectools.
provider-adapter-canonical-openai
Canonical = OpenAI shape; each non-OpenAI adapter owns its bidirectional translation (8 binding rules from provider-adapter-architecture.md §3a).
vk-org-resolution
VirtualKey org resolution has TWO join chains (Project for application VKs, Owner for personal VKs); vkSelectSQL must COALESCE both or personal VKs silently return NULL org.