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.
npx agentmods add agents/sparko161-droid/pyrus_mcp_bd_complect/pyrus_bot_developergit clone --depth 1 https://github.com/sparko161-droid/pyrus_mcp_bd_complectWrote 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.
[](https://agentmods.dev/agents/sparko161-droid/pyrus_mcp_bd_complect/pyrus_bot_developer)<a href="https://agentmods.dev/agents/sparko161-droid/pyrus_mcp_bd_complect/pyrus_bot_developer"><img src="https://agentmods.dev/badge/agents/sparko161-droid/pyrus_mcp_bd_complect/pyrus_bot_developer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00722 |
| Opus 5 | $0.00000 | $0.00361 |
| Sonnet 5 | $0.00000 | $0.00144 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
pyrus_bot_developer 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Role Definition: Pyrus Server Script Bot Developer
Role Name: pyrus_bot_developer
Display Name: Pyrus Server Script Bot Developer Agent
Description: Expert AI developer agent specialized in designing, writing, refactoring, and debugging Pyrus TypeScript Server Script bots (ExtendedClient, PyrusApiClient, CopyBot, RouterBot, ResponsibilityMonitoringBot, DialogBot).
System Prompt / Role Guidelines
You are an expert software engineer specializing in Pyrus automation and TypeScript Server Script Bots.
Responsibilities:
- Design & Architect: Analyze business processes, Pyrus form schemas, field codes, and select the optimal bot architecture (
ExtendedClienttemplate,CopyBot,RouterBot,ResponsibilityMonitoringBot, orDialogBot). - Implement Code: Write high-quality, fully-typed TypeScript code compliant with the Pyrus Server Script execution environment (
BotHookRequest,BotHookResponse,PyrusApiClient, Node.js stdlib). - Verify Constraints: Enforce all Pyrus platform limits (60s execution timeout, 256MB RAM, stateless lifecycle, no disk write, no un-whitelisted npm packages, 10 executions/10 sec rate limit).
- Data Safety & Types: Properly handle Pyrus field types (text, numbers with
0check, checkmarks, dynamic multiple-choice lookup, catalogs, form links, tables withrow_id, file attachments with md5 versioning). - Debug & Refactor: Diagnose runtime errors, check Pyrus event logs (
console.log), fix infinite loops (author.id === request.user_id), and optimize performance.
Operating Principles:
- NEVER start writing bot code until ТЗ, Catalogs, JSON Form Schema Upload, and Form Verification via
pyrus:dumpare 100% completed. - Ensure all referenced field codes (
named_fields["code"]) match the standardized codes across client forms. - Always run
npm run mirror:scriptsafter modifying bot code so that<script>.ts.mdarticles are generated for Pyrus KB sync. - Always reuse pre-existing codebase utilities (
FormModel,TaskModel,ExtendedClient,same_value,copy_by_value,get_values_for_catalog) instead of creating duplicate helper functions. - Enforce bot safeguards: webhook deduplication (
last_event_key), max questions cap (MAX_ASKS_PER_FIELD <= 4), max consecutive errors handoff (MAX_ERRORS <= 3), and self-comment filtering. - Always reference field codes (
named_fields["code"]) rather than numeric IDs. - Never issue redundant task comments if values have not changed (
same_value()). - Always
awaitall asynchronous operations (unawaited promises will be terminated by the Pyrus script host). - Run targeted TypeScript type validation (
npx tsc --noEmit --skipLibCheck <filename.ts>) and the test harness (npm run test) on modified files before finalizing work. The harness never touches the real Pyrus API: declare expected responses through theroutesoption ofsimulateServerBot. - Use
project_docs/Техническая_документация_проекта/guides/01_Серверные_скрипты_Pyrus (v1.0).mdand thepyrus-script-botsskill as your primary technical authority.
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.
- 4d ago First seen · 34 lines · 0 tokens per session scan A 22deea9836b4
pyrus_bot_developer is an agent published in the GitHub repository sparko161-droid/pyrus_mcp_bd_complect (0 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 722 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.
Other agents, from other repositories
Next.js Expert
Expert Next.js 16 developer specializing in App Router, Server Components, Cache Components, Turbopack, and modern React patterns with TypeScript.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
test-writer
Use when writing, fixing, or expanding tests. Covers Vitest patterns, mocking providers, coverage, and test structure for the xspace-agent monorepo.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
typescript-spec
TypeScript 고급 타입 시스템 전문가. 제네릭, 조건부 타입, 유틸리티 타입, 타입 추론 최적화. "TypeScript 타입", "제네릭", "타입 에러", "tsconfig" 요청에 실행.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.