botpress-adk

botpress-adk is a cursor rule for Cursor from parzival1l/Altru. It costs 0 tokens per session (4,034 once invoked), scanned A, original, MIT.

A set of rules for Botpress ADK, a TypeScript framework and command-line tool for building AI agents that run on Botpress Cloud.

In plain words
What is it for?
Building and debugging Botpress agents with conversations, workflows, tools, actions, triggers, data tables, knowledge bases, configuration, and evaluations.
Why use it?
It helps developers use the framework's supported building blocks and current documentation instead of guessing at changing APIs or calling lower-level services unnecessarily.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: positional $N argument.

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/parzival1l/altru/botpress-adk
Clone the repo
git clone --depth 1 https://github.com/parzival1l/Altru

Made for: Cursor.

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 botpress-adk

README.md
[![agentmods](https://agentmods.dev/badge/rules/parzival1l/altru/botpress-adk.svg)](https://agentmods.dev/rules/parzival1l/altru/botpress-adk)
Your own site
<a href="https://agentmods.dev/rules/parzival1l/altru/botpress-adk"><img src="https://agentmods.dev/badge/rules/parzival1l/altru/botpress-adk.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 4,034 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 5.1 $0.00000 $0.04034
Opus 5 $0.00000 $0.02017
Sonnet 5 $0.00000 $0.00807
Haiku 4.5 $0.00000 $0.00403

Measured 5d ago against content hash eb73d306f17c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

botpress-adk 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 5d 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.

.cursor/rules/botpress-adk.mdc · 423 lines

How it starts

The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Botpress ADK — Cursor Skill

You are assisting with a Botpress ADK project. The ADK is a TypeScript framework and CLI for building AI agents that deploy to Botpress Cloud. Botpress handles hosting, scaling, and channel delivery; the developer writes conversations, workflows, tools, actions, and triggers as code.

Authoritative docs index: https://botpress.com/docs/llms.txt Per-page markdown: append .md to any docs URL (e.g. https://botpress.com/docs/adk/conversations/tools.md).

Operating principles

  1. Verify before inventing. ADK APIs change. If you are unsure of a signature, fetch the relevant .md doc page rather than guessing. Common pages: adk/quickstart, adk/cli-reference, adk/conversations/setup, adk/conversations/tools, adk/conversations/ai-execution, adk/workflows/create, adk/external/actions, adk/external/triggers, adk/data/tables, adk/data/knowledge, adk/zai/overview, adk/testing/evals.
  2. Prefer ADK primitives over raw API calls. Use Conversation, Autonomous.Tool, Workflow, Action, Trigger, Table, Knowledge, and adk.zai rather than calling Botpress REST APIs directly from inside the bot runtime.
  3. One primitive per file. The ADK auto-discovers primitives by file. Do not register manually.
  4. Use Zod for all schemas. input, output, conversation state, table columns, and Zai extraction targets are all Zod.
  5. Type-safe channels. Avoid channel: "*" in production handlers. Pin to a specific channel (e.g. webchat.channel, slack.channel) so message payloads are typed.
  6. Run locally first. adk dev runs hot reload on port 3000 (bot) and 3001 (console). adk chat is the loopback test client. Ask the user to run these before deploying.
  7. Never deploy without explicit confirmation. adk deploy ships to Botpress Cloud. Surface the command, do not run it autonomously.

Read the full file on GitHub · 423 lines

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. 5d ago First seen · 423 lines · 0 tokens per session scan A eb73d306f17c

Subscribe to this mod's changes

botpress-adk is a cursor rule published in the GitHub repository parzival1l/Altru (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,034 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.