kaisa-kucherenko

17 mods in 1 plugin, 1 repository, 23 stars between them.

agatha

01

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A detailed code-review agent that examines security, architecture, correctness, and maintainability. It is designed for changes where subtle bugs or hidden dependencies matter.

not rated 23 +3 changed 18d ago A 0 tokens original MIT

arthur

02

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A read-only wrapper that sends a carefully scoped code-review request to the Codex command-line tool for a second opinion.

not rated 23 +3 changed 18d ago B 0 tokens original MIT

dash

03

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A fast code-review assistant that examines a change set, also called a diff, and checks the surrounding code when needed. It focuses on finding concrete correctness, security, and business-logic problems, with each finding tied to a file and line.

not rated 23 +3 changed 18d ago A 0 tokens original MIT

geralt

04

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A backend coding agent named after Geralt from The Witcher. It implements specified work in modern Python, with attention to asynchronous code, PostgreSQL, testing, and practical design.

not rated 23 +3 changed 1mo ago A 121 tokens original MIT

gilfoyle

05

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A read-only security-audit agent that examines software for vulnerabilities such as broken access controls, injection, exposed secrets, and privacy leaks. It reports issues but does not fix them.

not rated 23 +3 changed 1mo ago A 0 tokens original MIT

jobs

06

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A UI and UX design specialist that creates design systems and screen specifications before implementation. It covers colors, typography, spacing, components, and accessibility.

not rated 23 +3 4d ago A 116 tokens original MIT

lauda

07

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A read-only code-analysis assistant that looks for causes of slow software and explains them. It examines issues such as repeated database queries, unnecessary waiting, expensive agent prompts, cold starts, and web performance problems.

not rated 23 +3 4d ago A 0 tokens original MIT

lyutik

08

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A frontend coding agent for building and reviewing React and Next.js applications with TypeScript. It also explains its implementation choices for developers who mainly work on backend code.

not rated 23 +3 changed 1mo ago A 142 tokens original MIT

handoff

09

kaisa-kucherenko/claude-code-flow

Skill Claude Code

A way to save the current state of a coding task in a handoff file for a later session. The file records what remains to be done and how the next session should continue.

not rated 23 +3 4d ago A SkillSpector: pass 130 tokens original MIT

pickup

10

kaisa-kucherenko/claude-code-flow

Skill Claude CodeCodex

A workflow for continuing work from a handoff file, which records what a previous session completed and what should happen next. It checks that the recorded project state still matches reality before continuing.

not rated 23 +3 4d ago A 106 tokens original MIT

ariel

11

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A diagramming agent turns a system or process into Mermaid diagrams, a text format for flowcharts and other diagrams. It can depict request sequences, database relationships, classes, states, architecture, and schedules without redesigning the system.

not rated 23 +3 4d ago A 125 tokens original MIT

adr

12

kaisa-kucherenko/claude-code-flow

Skill Claude Code

An Architecture Decision Record (ADR) is a written log of important software design choices and the reasons behind them. It links several decisions into a clear description of how a feature should work.

not rated 23 +3 changed 18d ago A 142 tokens original MIT

implement

13

kaisa-kucherenko/claude-code-flow

Skill Claude Code

Runs ONE phase of a phase spec (written by /spec) through the full cycle: find the next phase from the live handoff, brief the user first, launch the implementer, freeze the tree, gate the diff against the phase's Acceptance, external review of the user's choice, local testing, commit, mark done, update the handoff.…

not rated 23 +3 4d ago A 140 tokens original MIT

twix

14

kaisa-kucherenko/claude-code-flow

Skill Claude Code

A two-reviewer workflow for examining a code change and combining the reviewers' findings into one verdict. It can review uncommitted changes or another scope named by the user.

not rated 23 +3 changed 18d ago A 116 tokens original MIT

dean

15

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A pytest test reviewer that checks whether automated tests really test the intended behavior. Pytest is a Python tool for running tests.

not rated 23 +3 4d ago A 0 tokens original MIT

sam

16

kaisa-kucherenko/claude-code-flow

Agent Claude Code

A pytest test-writing agent that derives tests from the stated behavior of Python code. It checks that each test targets a real bug and verifies that the test can fail when the code is changed incorrectly.

not rated 23 +3 4d ago A 0 tokens original MIT

pytest-quality

17

kaisa-kucherenko/claude-code-flow

Skill Claude CodeCodex

The bar for pytest unit tests that can actually fail when the code is wrong — every test names the break it catches, expected values come from an independent oracle, fixture values discriminate between branches, mocks sit only at the external edge, and nothing is written for count or coverage. Preloaded by the…

not rated 23 +3 4d ago C 82 tokens original MIT

richmond

18

kaisa-kucherenko/claude-code-flow

Plugin Claude Code

Bundles 4 hooks

AFC Richmond persona: match HUD above the prompt, Roy Kent sounds, Nelson Road themes, locker-room spinner and status lines, a /timer break screen.

not rated 23 +3 changed 4d ago A tokens not measured original 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: