sdk-python

A set of rules for using the AgentHelm Python SDK, a software toolkit for connecting and running agents.

In plain words
What is it for?
Connecting to AgentHelm, defining tools and message handlers, reporting progress, saving checkpoints, tracking model tokens, and keeping a long-running agent listening.
Why use it?
It gives Python projects consistent patterns for marking read-only, side-effecting, and high-risk actions, while tracking progress and usage.

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/jayasukuv11-beep/agenthelm/sdk-python
Clone the repo
git clone --depth 1 https://github.com/jayasukuv11-beep/agenthelm

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 274 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 $0.00000 $0.00274
Opus 5 $0.00000 $0.00137
Sonnet 5 $0.00000 $0.00055
Haiku 4.5 $0.00000 $0.00027

Measured yesterday against content hash 5cd83c89ec52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdk-python 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 yesterday.

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/sdk-python.mdc · 26 lines

What it actually says

AgentHelm Python SDK Rules

Core Initialization

  • Always use import agenthelm.
  • dock = agenthelm.connect("YOUR_KEY") is the standard entry point.

Tool Decoration (Safety First)

  • Read-only tools: Use @dock.read (e.g. searching, listing files).
  • Side-effect tools: Use @dock.side_effect(max_retries=3) (e.g. sending Slack, writing small files).
  • High-risk tools: Use @dock.irreversible(confirm="telegram") (e.g. deleting users, executing trades).

Observability Best Practices

  • Call dock.progress(percent, "Message") inside long-running loops.
  • Use dock.checkpoint("Step Name", state) before executing any function that interacts with external APIs.
  • Ensure dock.track_tokens(used, model) is called after every generic LLM call.

Handling Communications

  • Define @dock.on_dispatch to handle incoming tasks from the AgentHelm ecosystem.
  • Define @dock.on_chat to handle direct user interactions.
  • Always call dock.listen() to keep the agent alive if it's a long-running service.
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. yesterday First seen · 26 lines · 0 tokens per session scan A 5cd83c89ec52

Subscribe to this mod's changes

sdk-python is a cursor rule published in the GitHub repository jayasukuv11-beep/agenthelm (4 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 274 tokens. 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.