subagent-dev

Execute tasks.md tasks via implementer and reviewer subagents.

151|20|Updated Feb 11, 2026

Search Tags:#code review #task automation #subagents #workflow execution #git commits #1c development

Ready to run

npx skills add https://github.com/Arman-Kudaibergenov/1c-ai-development-kit --skill subagent-dev-arman-kudaibergenov

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-dev
Source: https://github.com/Arman-Kudaibergenov/1c-ai-development-kit/tree/main/.claude/skills/subagent-dev
Command: npx skills add https://github.com/Arman-Kudaibergenov/1c-ai-development-kit --skill subagent-dev-arman-kudaibergenov

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Eliminates slow, step-by-step execution by enabling autonomous parallel implementation and review for tasks described in tasks.md, so larger 1C development efforts can progress without constant user coordination.

Core Features & Use Cases

Autonomous implementer + reviewer loop: executes each task with a dedicated implementer and a single-pass reviewer that checks both specification match and code quality.
No user prompts between steps: continues through up to two correction iterations per task without asking the user, unless a blocker prevents progress.
Progress tracking in tasks.md: marks tasks from [ ] to [x] as work completes successfully.

Quick Start

Use the subagent-dev skill to complete a multi-task feature described in tasks.md by calling it with the path to that file.

Frequently Asked Questions about subagent-dev

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate tasks.md execution with subagents for 1C development?▼

Automating tasks.md execution involves delegating each task to an implementer and a reviewer subagent for one-pass compliance and code-quality validation. This allows complex 1C project workstreams to progress autonomously without user coordination.

Can I run multi-step 1C development tasks without user prompts between steps?▼

Yes, autonomous subagent execution continues through up to two correction iterations per task without user prompts. It only stops to escalate blockers when dependencies or contradictions prevent continuation.

How does the subagent reviewer feedback loop work for code quality validation?▼

The reviewer feedback loop works by having a dedicated reviewer subagent check both specification match and code quality after implementation. It runs up to two correction iterations autonomously before updating the task state.

What do I need to set up before running autonomous task automation on a 1C project?▼

You need to prepare a tasks.md file containing the atomic task steps and a design.md file. The automation requires reading both files to execute parallel subagent workflows and update task progress accurately.

How to track progress when autonomously executing 1C project workstreams?▼

Progress tracking is handled directly within tasks.md by marking completed items from [ ] to [x]. The system updates the file state automatically as the implementer and reviewer subagents finish each task successfully.

What happens when a blocker prevents continuation during autonomous task execution?▼

When dependencies or contradictions prevent continuation, the system stops the autonomous loop and produces a final commit-oriented report. This report escalates the specific blockers preventing further progress on the tasks.md workstream.