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 skills add kimss-ai/kimss-python-sdk --skill kimss-sdkgit 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/skills/kimss-ai/kimss-python-sdk/kimss-sdk)<a href="https://agentmods.dev/skills/kimss-ai/kimss-python-sdk/kimss-sdk"><img src="https://agentmods.dev/badge/skills/kimss-ai/kimss-python-sdk/kimss-sdk/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/skills/kimss-ai/kimss-python-sdk/kimss-sdk"><img src="https://agentmods.dev/badge/skills/kimss-ai/kimss-python-sdk/kimss-sdk.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 | $0.00044 | $0.00751 |
| Opus 5.5 | $0.00018 | $0.00300 |
| Sonnet 5.5 | $0.00009 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
kimss-sdk 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 24d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kimss Python SDK / Gateway
When to use
- Routing app traffic through Kimss (identity, audit, kill switch).
- Optional DevOps: register external agents, report BYO usage.
Preferred inference (no Kimss SDK)
Keep the native SDK already in the app.
OpenAI — pip install openai, base_url=https://api.kimss.ai/v1:
import os
from openai import OpenAI
client = OpenAI(
base_url=os.getenv("KIMSS_GATEWAY_URL", "https://api.kimss.ai/v1"),
api_key=os.getenv("KIMSS_API_KEY") or os.getenv("KIMSS_WORKSPACE_KEY"),
)
resp = client.chat.completions.create(
model=os.getenv("KIMSS_MODEL", "custom:your-model"),
messages=[{"role": "user", "content": "Hello"}],
extra_headers={
"X-Kimss-Agent-Id": os.getenv("KIMSS_AGENT_ID", "my_agent"),
"X-Kimss-Agent-Name": os.getenv("KIMSS_AGENT_NAME", "My Agent"),
},
)
Anthropic — pip install anthropic, base_url=https://api.kimss.ai (SDK appends /v1/messages):
import os
from anthropic import Anthropic
client = Anthropic(
base_url=os.getenv("ANTHROPIC_BASE_URL", "https://api.kimss.ai"),
api_key=os.getenv("KIMSS_API_KEY") or os.getenv("KIMSS_WORKSPACE_KEY"),
)
resp = client.messages.create(
model=os.getenv("KIMSS_MODEL", "custom:your-model"),
max_tokens=1024,
messages=[{"role": "user", "content": "Hello"}],
extra_headers={
"X-Kimss-Agent-Id": os.getenv("KIMSS_AGENT_ID", "my_agent"),
"X-Kimss-Agent-Name": os.getenv("KIMSS_AGENT_NAME", "My Agent"),
},
)
See examples/00b_anthropic_proxy.py.
Control plane (optional)
pip install kimss
from kimss import KimssClient
client = KimssClient(api_key="kimss_...", base_url="https://api.kimss.ai")
client.agents.register(name="Database Auditor", agent_id="enterprise_db_auditor")
Deprecated (do not generate new call sites)
client.agents.run, client.chat, Agent.query, client.models.create, MCP kimss_chat / kimss_run_agent / kimss_complete.
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.
- 24d ago Changed 389c6bab945b
- 2mo ago First seen · 86 lines · 44 tokens per session scan A 592c2ca8e8b1
kimss-sdk is a skill published in the GitHub repository kimss-ai/kimss-python-sdk (1 stars, last pushed 7d ago), licensed MIT. It adds 44 tokens to every session and 751 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 2026-08-31.
kimss-sdk compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kimss-sdkkimss-ai/kimss-python-sdk | Skill | 1 | 7d ago | MIT | A | 44 | Cursor |
| workflow-ai-codingw8123/EnterpriseAgentFramework | Skill | 1.0k | today | MIT | A | 85 | Claude Code, Codex |
| reachai-onboardingw8123/EnterpriseAgentFramework | Skill | 1.0k | today | MIT | A | 89 | Codex |
| omni-inferencediegosouzapw/OmniRoute | Skill | 83k | 5d ago | MIT | A | 47 | Claude Code, Codex |
| omni-providersdiegosouzapw/OmniRoute | Skill | 83k | 5d ago | MIT | A | 45 | Claude Code, Codex |
| omni-authdiegosouzapw/OmniRoute | Skill | 83k | 5d ago | MIT | A | 36 | Claude Code, Codex |
| omni-combos-routingdiegosouzapw/OmniRoute | Skill | 83k | 5d ago | MIT | A | 44 | Claude Code, Codex |