Insajin/autopus-adk

Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.

This repository also configures its own agents. See what autopus-adk tells them →

111Stars on the repository
105Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

monitor-patterns

49

Insajin/autopus-adk

Skill Claude CodeCodex

Monitor tool usage patterns and grep --line-buffered compatibility guide.

not rated 111 +2 yesterday A SkillSpector: pass 16 tokens original MIT

performance

50

Insajin/autopus-adk

Skill Claude CodeCodex needs its repo

A guide to measuring and improving the speed and resource use of Go programs. It explains benchmarks and profiling, which records where a program spends time or memory.

not rated 111 +2 yesterday A SkillSpector: pass 19 tokens original MIT

planning

51

Insajin/autopus-adk

Skill Claude CodeCodex

A guide for planning software features and turning requests into clear requirements. It uses EARS, a plain format for stating what a system must do under specific conditions.

not rated 111 +2 yesterday A SkillSpector: pass 12 tokens original MIT

playwright-cli

52

Insajin/autopus-adk

Skill Claude CodeCodex

Skill "playwright-cli" from Insajin/autopus-adk, covering browser automation with playwright-cli, quick start, commands, core and navigation.

not rated 111 +2 yesterday A SkillSpector: warn 32 tokens original MIT

prd

53

Insajin/autopus-adk

Skill Claude CodeCodex

A guide for writing a PRD, or Product Requirements Document, which explains what a product or feature should achieve and who it is for. It covers goals, users, success measures, limits, prior work, and excluded scope.

not rated 111 +2 yesterday A SkillSpector: pass 11 tokens original MIT

product-discovery

54

Insajin/autopus-adk

Skill Claude CodeCodex

Product discovery workflow with OST, assumption testing, and interview scripts.

not rated 111 +2 yesterday A SkillSpector: pass 16 tokens original MIT

refactoring

55

Insajin/autopus-adk

Skill Claude CodeCodex

A set of techniques for improving code structure while keeping its existing behavior unchanged. Refactoring means reorganizing code without intentionally changing what it does.

not rated 111 +2 yesterday A SkillSpector: pass 20 tokens original MIT

review

56

Insajin/autopus-adk

Skill Claude CodeCodex

A structured checklist for reviewing software code. It covers tests, readability, consistency, security, and whether changes can be tracked.

not rated 111 +2 yesterday A SkillSpector: pass 12 tokens original MIT

security-audit

57

Insajin/autopus-adk

Skill Claude CodeCodex

A security review guide based on the OWASP Top 10, a widely used list of common web application security risks. It covers access control, encryption, injection, authentication, dependencies, and logging.

not rated 111 +2 yesterday A SkillSpector: pass 15 tokens original MIT

spec-review

58

Insajin/autopus-adk

Skill Claude CodeCodex

Multi-provider SPEC review gate skill.

not rated 111 +2 yesterday A SkillSpector: pass 9 tokens original MIT

subagent-dev

59

Insajin/autopus-adk

Skill Claude CodeCodex

A guide for designing and coordinating subagents, which are smaller coding agents delegated specific tasks. It covers their roles, permissions, tools, models, limits, memory, and isolated workspaces.

not rated 111 +2 yesterday A SkillSpector: pass 19 tokens original MIT

tdd

60

Insajin/autopus-adk

Skill Claude CodeCodex

A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.

not rated 111 +2 yesterday A SkillSpector: pass 11 tokens original MIT

testing-strategy

61

Insajin/autopus-adk

Skill Claude CodeCodex

A testing guide that explains how to combine unit, integration, contract, and end-to-end tests. End-to-end tests check complete user flows, while integration tests check components working together.

not rated 111 +2 yesterday A SkillSpector: pass 20 tokens original MIT

using-autopus

62

Insajin/autopus-adk

Skill Claude CodeCodex

An installation and usage guide for Autopus-ADK, a harness that adds coding methods, model routing, hooks, session continuity, and project quality rules to coding command-line tools.

not rated 111 +2 yesterday A SkillSpector: pass 16 tokens original MIT

verification

63

Insajin/autopus-adk

Skill Claude CodeCodex

A verification guide for checking an implementation against its requirements and quality gates, including builds, tests, race checks, coverage, linting, and static analysis.

not rated 111 +2 yesterday A SkillSpector: pass 16 tokens original MIT

worktree-isolation

64

Insajin/autopus-adk

Skill Claude CodeCodex

Worktree isolation for parallel agent execution in the pipeline.

not rated 111 +2 yesterday A SkillSpector: pass 15 tokens original MIT

writing-skills

65

Insajin/autopus-adk

Skill Claude Code

A guide for writing technical documentation and defining skills for Claude Code and related coding-agent tools. It covers skill files, settings, templates, and reusable instructions.

not rated 111 +2 yesterday A SkillSpector: pass 21 tokens original MIT

frontend-skill

66

Insajin/autopus-adk

Skill Claude CodeCodex

Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter.

not rated 111 +2 yesterday A 58 tokens copy · 81% MIT

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