Saik0s/agent-loop

πŸš€ Agentic Engineering: A guide for orchestrating specialized AI agents in software development. Demonstrates workflows where human orchestrators direct AI personas to build, test, and deploy code collaboratively.

19Stars on the repository
23Mods indexed here, across every type
1y agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

analyze

01

Saik0s/agent-loop

Command Claude Code

Analyzes the codebase for correctness, architecture, quality, security, and performance, providing a prioritized list of actionable issues.

not rated 19 1y ago A 25 tokens

build

02

Saik0s/agent-loop

Command Claude Code

Builds a new feature based on a description, creating the necessary code and tests.

not rated 19 1y ago A 17 tokens

Saik0s/agent-loop

Command Claude Code

Create well-formatted commits with conventional commit messages and emojis, with pre-commit checks.

not rated 19 1y ago A 18 tokens

commit

04

Saik0s/agent-loop

Command Claude Code

Analyzes staged changes and generates a commit message that follows the Conventional Commits specification.

not rated 19 1y ago A 17 tokens

create-command

05

Saik0s/agent-loop

Command Claude Code

Guide for creating new custom Claude commands with proper structure.

not rated 19 1y ago A 11 tokens

debug

06

Saik0s/agent-loop

Command Claude Code

Troubleshoot issues by analyzing errors, logs, and execution paths to identify root causes.

not rated 19 1y ago A 18 tokens

dependencies

07

Saik0s/agent-loop

Command Claude Code

Manage project dependencies including updates, security audits, and conflict resolution.

not rated 19 1y ago A 13 tokens

enhance

09

Saik0s/agent-loop

Command Claude Code

Intelligently enhances user input by generating a structured task map, refining an ambiguous query, or improving a code snippet.

not rated 19 1y ago A 24 tokens

multi-mind-zen

11

Saik0s/agent-loop

Command Claude Code

Execute a multi-specialist collaborative analysis where every subagent delegates all substantive work to the three zen tools: mcpzenchat, mcpzenconsensus, and mcpzenanalyze.

not rated 19 1y ago A 45 tokens

orchestrate

12

Saik0s/agent-loop

Command Claude Code

Delegates a given command to the most appropriate specialist agent for managed execution.

not rated 19 1y ago A 15 tokens

Saik0s/agent-loop

Command Claude Code

Approach task implementation methodically with careful planning, execution, and best practices.

not rated 19 1y ago A 16 tokens

plan-repoprompt

14

Saik0s/agent-loop

Command Claude Code

Generates a file-aware implementation plan for a new feature or task exclusively through Repoprompt.

not rated 19 1y ago A 19 tokens

plan

15

Saik0s/agent-loop

Command Claude Code

Creates a detailed, file-aware implementation plan for a new feature or task.

not rated 19 1y ago A 15 tokens

propose-solutions

17

Saik0s/agent-loop

Command Claude Code

Generates and compares distinct, viable solutions for a given problem, each with pros and cons, and provides a final recommendation.

not rated 19 1y ago A 25 tokens

setup

18

Saik0s/agent-loop

Command Claude Code

Initialize new projects or configure development environments with best practices.

not rated 19 1y ago A 11 tokens

spec

19

Saik0s/agent-loop

Command Claude Code

Creates a detailed feature specification document.

not rated 19 1y ago A 7 tokens

tdd

20

Saik0s/agent-loop

Command Claude Code

Guides the Test-Driven Development (TDD) of a new feature using the Red-Green-Refactor cycle.

not rated 19 1y ago A 25 tokens

test

21

Saik0s/agent-loop

Command Claude Code

Generates a comprehensive test suite (unit, integration, and E2E) for a given code component, function, or feature.

not rated 19 1y ago A 27 tokens

update-project-docs

22

Saik0s/agent-loop

Command Claude Code

You will generate LLM-optimized documentation with concrete file references and flexible formatting.

not rated 19 1y ago A 16 tokens

Saik0s/agent-loop

Command Claude Code

Orchestrates the generation of LLM-optimized documentation by spawning specialized subagents for different documentation areas. All analysis is performed on source code, not existing docs.

not rated 19 1y ago A 33 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page β€” the rest are on their repository pages: