entwickler-agent

entwickler-agent is a skill for Claude Code, Codex from ellmos-ai/bach. It costs 49 tokens per session (2,243 once invoked), scanned A, original, MIT.

An autonomous software-development assistant for managing projects and tasks, with a development workflow for planning, writing, and checking code.

In plain words
What is it for?
Use it to create and manage projects, add and prioritize tasks, view status reports, and run the described planning, coding, and checking workflow.
Why use it?
It gives projects and tasks a persistent structure and separates planning, implementation, and quality checks into distinct stages.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create and manage projects, add and prioritize tasks, view…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ellmos-ai/bach/entwickler
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.

Any agent
npx skills add ellmos-ai/bach --skill entwickler
Clone the repo
git clone --depth 1 https://github.com/ellmos-ai/bach

Made for: Claude Code, Codex.

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 entwickler-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/ellmos-ai/bach/entwickler.svg)](https://agentmods.dev/skills/ellmos-ai/bach/entwickler)
Your own site
<a href="https://agentmods.dev/skills/ellmos-ai/bach/entwickler"><img src="https://agentmods.dev/badge/skills/ellmos-ai/bach/entwickler.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,243 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00049 $0.02243
Opus 5 $0.00024 $0.01122
Sonnet 5 $0.00010 $0.00449
Haiku 4.5 $0.00005 $0.00224

Measured 6d ago against content hash 0729ad47974b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

entwickler-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 6d 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.

system/agents/entwickler/SKILL.md · 457 lines

How it starts

The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.

============================================================ ENTWICKLER-AGENT V0.2.0

Autonomer Software-Entwicklungs-Agent

🤖 Selbstständige Projekt- und Task-Verwaltung mit Code-Entwicklung


KERNFUNKTIONEN

[✅ Phase 1 (IMPLEMENTIERT)]

  • Projekt-Management: Projekte erstellen, laden, verwalten
  • Task-Management: Tasks hinzufügen, priorisieren, abarbeiten
  • Status-Reporting: Übersicht über Projekte und Tasks
  • Persistenz: JSON-basierte Datenhaltung

[⏳ Phase 2-6 (GEPLANT)]

  • Code-Analyse (via coding-tools)
  • Service-Integration (Editor, Compiler)
  • Testing
  • Deployment

[✅ Entwicklungsschleife Advanced (INTEGRIERT)]

Pfad: SOFTWARE/prio3/A3 Entwicklungsschleife Advanced/entwicklerschleife_advanced_v3.py

KI-gestützte Software-Entwicklung mit automatischer Phasen-Transition:

Phase Rolle Funktion
Planer Architektur Analysiert Anforderungen, plant Struktur
Coder Implementierung Generiert Code nach Plan
Checker Qualität Prüft, testet, verbessert

Features:

  • Automatische Phasen-Transition (kein manueller Button)
  • Professioneller Editor mit Zeilennummern
  • Robuste API-Integration mit Retry-Logik
  • Dark Mode GUI
  • Multi-Language: Python, JavaScript, TypeScript, Java, C++, C#, Go, Rust, Ruby, PHP, Swift, Kotlin

Verwendung: python entwicklerschleife_advanced_v3.py


VERWENDUNG

[Programmatisch (Python)]

from agents.Entwickler.agent import EntwicklerAgent

============================================================ AGENT INITIALISIEREN

agent = EntwicklerAgent()

============================================================ PROJEKT ERSTELLEN

project_id = agent.create_project( name="MeinProjekt", template="python_cli", description="Ein CLI-Tool" )

============================================================ TASK HINZUFÜGEN

task_id = agent.add_task( title="Login-Feature implementieren", description="User-Login mit OAuth", task_type="feature", priority="high", project_id=project_id )

============================================================ NÄCHSTEN TASK BEARBEITEN

result = agent.process_next_task()

============================================================ STATUS ABRUFEN

print(agent.status_report())

[CLI (Testing)]

python agent.py

Ausgabe: === Entwickler-Agent v0.1.0 ===

=== ENTWICKLER-AGENT STATUS ===

Projekte: 1 (Aktiv: 1) Tasks: 3 gesamt

  • Ausstehend: 2
  • In Arbeit: 1
  • Abgeschlossen: 0

API-REFERENZ

[Projekt-Management]

create_project(name, template, description)

Erstellt neues Projekt

Parameter:

  • name (str): Projekt-Name
  • template (str): Template-Typ (python_cli, python_gui, python_library)
  • description (str): Beschreibung

Returns: project_id (str)

Beispiel: project_id = agent.create_project( "WebScraper", "python_cli", "Tool zum Scrapen von Websites" )

load_project(project_id)

Lädt Projekt-Daten

Returns: Dict oder None

list_projects(status=None)

Listet Projekte

Parameter:

  • status (str, optional): Filter nach Status (active, archived)

Returns: List[Dict]


[Task-Management]

add_task(title, description, task_type, priority, project_id)

Fügt Task zur Queue hinzu

Parameter:

  • title (str): Task-Titel
  • description (str): Beschreibung
  • task_type (str): bugfix|feature|optimization|refactor|test|documentation
  • priority (str): low|normal|high|critical
  • project_id (str, optional): Zugehöriges Projekt

Returns: task_id (str)

get_next_task()

Holt nächsten Task (höchste Priorität)

Returns: Dict oder None

Read the full file on GitHub · 457 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. 6d ago First seen · 457 lines · 49 tokens per session scan A 0729ad47974b

Subscribe to this mod's changes

entwickler-agent is a skill published in the GitHub repository ellmos-ai/bach (7 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 2,243 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.

Related

Other skills, from other repositories

pydanticai

Build type-safe AI agents and graph-based workflows with PydanticAI and PydanticGraph. Agent creation, function tools, capabilities, dependency injection, structured output, streaming, multi-agent patterns, testing, evals, and graph state machines. Use whenever you are building agents, tool-using LLM workflows, or…

magnus919/agent-skills · 93 tokens

dev-soft-agent

Automated software development pipeline. Scans projects, prioritizes tasks, analyzes code, and orchestrates development loops. Zero dependencies (Python stdlib only).

ellmos-ai/skills · 35 tokens

knowledge-transfer

Interview a person and turn their operating know-how (tacit knowledge) into the company brain: processes, rules with source, a glossary, decisions and open questions, written into the workspace. Use whenever someone needs to capture how a process actually gets done, before a key person leaves or retires, to onboard a…

yempik-ai/cowork-os · 148 tokens

cowork-os-core

Core operating rules for a cowork-os workspace. Use whenever working inside a Claude Cowork project that uses cowork-os (folders like context/, marketing/, website/, decisions/, signals/, reviews/), or on any strategy, marketing, content, website, or business-development task where decisions and context should persist…

yempik-ai/cowork-os · 137 tokens

senior-strategy-architect

Use proactively whenever the user asks for any strategy, plan, roadmap, growth plan, GTM, marketing, business, product, brand, pricing, sales, content, retention, fundraising, marketplace, partnerships, community, competitive response, launch, monetization, or business decision. Turns vague asks into senior-level…

yempik-ai/cowork-os · 145 tokens

pipeline-followup

Prepare draft follow-up emails for CRM deals that have gone quiet. Use whenever the person wants to chase deals with no reply, re-engage stalled opportunities, or "prepare the follow-ups" for their pipeline — e.g. "controlla la pipeline e preparami i follow-up", "chi non mi ha risposto?", "fammi le bozze per i deal…

yempik-ai/cowork-os · 156 tokens