kimss-create-agent

A guided procedure for creating a Kimss agent and sending its first message through MCP or the software development kit.

In plain words
What is it for?
Use it to create an owned agent, run an initial message, and continue the conversation with the returned conversation identifier.
Why use it?
It explains the required management permission, records the identifiers needed for follow-up messages, and clarifies what a permission error means.

Command

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 commands/kimss-ai/kimss-python-sdk/kimss-create-agent
Clone the repo
git clone --depth 1 https://github.com/kimss-ai/kimss-python-sdk
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 283 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00031 $0.00283
Opus 5 $0.00015 $0.00142
Sonnet 5 $0.00006 $0.00057
Haiku 4.5 $0.00003 $0.00028

Measured 2d ago against content hash 8280a48db227, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kimss-create-agent 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 2d 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.

commands/kimss-create-agent.md · 14 lines

What it actually says

Kimss — create agent and first run

  1. Prerequisites: User has a Kimss API key with management scope (required for POST /v1/agents/create / kimss_create_agent). Personal keys without management cannot create agents via API.
  2. Collect inputs: Display name, optional model deployment id, optional instructions/metadata.
  3. Create: Call MCP tool kimss_create_agent with at least name, or SDK client.agents.create(...). Persist returned assistant_id (and any thread_id / conversation hints returned by the API).
  4. First run: Call kimss_run_agent with assistant_id, message, no conversation_id yet — or SDK client.agents.run(assistant_id, message, stream=False).
  5. Threading: Store conversation_id from the result; pass it on follow-up calls as conversation_id (MCP) / same in SDK (maps to JSON thread_id).
  6. If 403: Key scope or agent ownership — do not retry with the same key; explain management scope or use an existing owned assistant_id.
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. 2d ago First seen · 14 lines · 31 tokens per session scan A 8280a48db227

Subscribe to this mod's changes

kimss-create-agent is a command published in the GitHub repository kimss-ai/kimss-python-sdk (1 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 283 once invoked, about $0.0002 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.