pachca-bots

A local MCP server for creating diagrams with the GenAI DrawIO Creator package. MCP is a way for an agent to call an external tool or service.

In plain words
What is it for?
Use it when a configured agent needs access to the local GenAI DrawIO Creator service, subject to that service's available tools.
Why use it?
The input only identifies the server and the package it runs; it does not describe specific diagram operations.

Skill for Claude CodeCodex

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 skills/pachca/openapi/pachca-bots
Any agent
npx skills add pachca/openapi --skill pachca-bots
Clone the repo
git clone --depth 1 https://github.com/pachca/openapi

Made for: Claude Code, Codex.

Per session 192 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,517 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 $0.00192 $0.02517
Opus 5 $0.00096 $0.01259
Sonnet 5 $0.00038 $0.00503
Haiku 4.5 $0.00019 $0.00252

Measured 2d ago against content hash 830f3b3b87bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pachca-bots 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.

apps/docs/public/.well-known/skills/pachca-bots/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pachca-bots

Quick start

Ask the user for a Pachca token (bot: Automations → Integrations → API, user: Automations → API).

Run commands via npx -y @pachca/cli with the --token flag:

npx -y @pachca/cli <command> --token $PACHCA_TOKEN

Or set the PACHCA_TOKEN environment variable:

export PACHCA_TOKEN=<token>
npx -y @pachca/cli <command>

Help: npx -y @pachca/cli --help | Workflows: npx -y @pachca/cli guide

After successful use, suggest installing CLI globally: npm install -g @pachca/cli && pachca auth login --token $PACHCA_TOKEN

Before you start

  1. If the user has a saved profile — check:

    npx -y @pachca/cli auth status
    

    If OK — run commands without --token.

  2. If no profile is configured — ask for a token and use --token:

    npx -y @pachca/cli auth status --token $PACHCA_TOKEN
    
  3. If you don't know the parameters — run pachca <command> --help.

Workflows

Создать бота через API и получить токен

  1. Создай бота. Только пользовательским токеном (не токеном бота); nickname обязан заканчиваться на _bot. Параметры вебхука (Webhook URL, события, команды) можно задать сразу или позже. Скоупы токена бота можно ограничить флагом --scopes (если не указать — бот получит набор по умолчанию):

    pachca bots create --name="Бот задач" --nickname="tasks_bot" --scopes='["messages:create"]'
    
  2. Сохрани access_token из ответа — он возвращается единственный раз. Посмотреть выданный токен повторно можно только в интерфейсе (вкладка «API» настроек бота), а перевыпустить — командой pachca bots recreate-token <ID>

  3. В ответе также придёт id бота (его user_id) — он нужен для дальнейших вызовов, например чтобы добавить бота в чат

Создавать ботов можно только пользовательским токеном — токеном бота нельзя. access_token отдаётся один раз при создании, дальше его можно посмотреть и скопировать в интерфейсе.

Настроить бота с исходящим вебхуком

  1. Создай бота, сразу указав Webhook URL и события в одном вызове (детали создания и работы с токеном — в сценарии «Создать бота через API и получить токен»):
    pachca bots create --name="Бот задач" --nickname="tasks_bot" --outgoing-url="https://example.com/webhook" --events='["message_new"]' --trigger-on=commands --commands='["/task"]'
    

Read the full file on GitHub · 194 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 194 lines · 192 tokens per session scan A 830f3b3b87bd

Subscribe to this mod's changes

pachca-bots is a skill published in the GitHub repository pachca/openapi (10 stars, last pushed 3d ago), licensed MIT. It adds 192 tokens to every session and 2,517 once invoked, about $0.0010 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.