kaisa-kucherenko/claude-code-flow

My working Claude Code setup: output styles, hooks, skills, agents

23Stars on the repository
22Mods indexed here, across every type
4d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

handoff

01

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

02

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

adr

03

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

04

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

05

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

pytest-quality

06

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

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: