agentmods.dev

kimss-forge

kimss-forge is a skill for Cursor from kimss-ai/kimss-python-sdk. It costs 66 tokens per session (392 once invoked), scanned A, original, MIT.

A Python library for building AI agents that can call tools and repeat model-and-tool steps. It can run locally with an OpenAI-compatible service and can optionally connect to the Kimss gateway for identity, auditing, and a stop switch.

In plain words
What is it for?
Use it to create local tool-calling agents, multi-step agent loops, or agents connected to Kimss. It is intended for Python projects and requires an OpenAI API key.
Why use it?
Writing the control loop for an agent from scratch requires handling model replies, tool calls, and multiple turns. This library supplies that loop and a defined place to add Python tools.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the kimss plugin — 3 skills, 3 commands, 1 MCP server shipped together

not rated 1repo 7d ago A scan 66 tokens original MIT

Good fit Use it to create local tool-calling agents, multi-step agent loops, or agents connected to Kimss. It is intended for Python projects and requires an OpenAI API key.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kimss-ai/kimss-python-sdk/kimss-forge
View source ↗ kimss-ai/kimss-python-sdk
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.

Any agent
npx skills add kimss-ai/kimss-python-sdk --skill kimss-forge
Clone the repo
git clone --depth 1 https://github.com/kimss-ai/kimss-python-sdk

Made for: Cursor.

Or install kimss, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 1 MCP server.

Wrote 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.

agentmods badge for kimss-forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimss-ai/kimss-python-sdk/kimss-forge/github.svg)](https://agentmods.dev/skills/kimss-ai/kimss-python-sdk/kimss-forge)
Your own site
<a href="https://agentmods.dev/skills/kimss-ai/kimss-python-sdk/kimss-forge"><img src="https://agentmods.dev/badge/skills/kimss-ai/kimss-python-sdk/kimss-forge/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.

agentmods 80×15 button for kimss-forge

Your own site · 80×15
<a href="https://agentmods.dev/skills/kimss-ai/kimss-python-sdk/kimss-forge"><img src="https://agentmods.dev/badge/skills/kimss-ai/kimss-python-sdk/kimss-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 392 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00066 $0.00392
Opus 5.5 $0.00026 $0.00157
Sonnet 5.5 $0.00013 $0.00078
Haiku 4.5 $0.00007 $0.00039

Measured 1mo ago against content hash 18639324a897, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kimss-forge 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.

skills/kimss-forge/SKILL.md · 59 lines

What it actually says

Kimss Forge (Cursor skill)

When to use

  • "Build a local AI agent" / "tool calling agent" / "agent with tools" in Python
  • Multi-turn model → tools → model loops
  • Connecting agents to Kimss for kill switch / identity / audit

Default code (local)

from kimss_forge import Agent, tool

@tool
def multiply(a: float, b: float) -> float:
    """Multiply two numbers."""
    return a * b

agent = Agent(model="gpt-4o-mini", tools=[multiply])
print(agent.run("What is 6 times 7?"))

Requires OPENAI_API_KEY. Optional OPENAI_BASE_URL.

Production (always include gateway="kimss")

agent = Agent(
    model="custom:your-vaulted-model",
    tools=[multiply],
    gateway="kimss",
    agent_id="my_agent",
    workspace_key="kimss_...",
)

Rules

  1. Prefer kimss_forge.Agent over inventing a custom hop loop.
  2. Never import Hermis server modules — proprietary.
  3. Kill switch is free on the Developer gateway; Authority Boundary / SSO / SCIM are paid.
  4. Point assistants at https://kimss.ai/docs/agent_harness and the package llm-context.md.

Install

pip install kimss-forge
# optional MCP:
pip install 'kimss-forge[mcp]'
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. 1mo ago First seen · 59 lines · 66 tokens per session scan A 18639324a897

Subscribe to this mod's changes

kimss-forge is a skill published in the GitHub repository kimss-ai/kimss-python-sdk (1 stars, last pushed 7d ago), licensed MIT. It adds 66 tokens to every session and 392 once invoked, about $0.0003 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 2026-09-14.

Building agentsai-agentsai-gatewayapi-gatewayenterprise-aigovernancellm-security
Related

kimss-forge compared with skills from other repositories

kimss-forge next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kimss-forgekimss-ai/kimss-python-sdkSkill17d agoMITA66Cursor
workflow-ai-codingw8123/EnterpriseAgentFrameworkSkill1.0ktodayMITA85Claude Code, Codex
agent-ai-codingw8123/EnterpriseAgentFrameworkSkill1.0ktodayMITA84Claude Code, Codex
reachai-onboardingw8123/EnterpriseAgentFrameworkSkill1.0ktodayMITA89Codex
AegisGateax128/AegisGateSkill721mo agoMITB0Claude Code, Codex
ai-guardianAIops-tools/AI-GuardianSkill07d agoMITA419Claude Code
omni-mcpdiegosouzapw/OmniRouteSkill83k5d agoMITA48Claude Code, Codex