Command Claude Code
A writing checker for spotting common signs of AI-generated prose in Korean or English, with optional manual rewriting or editing. It treats these signs as clues rather than proof that AI wrote the text.
Command Claude Code
A command that records reusable solutions and design decisions in existing project documentation. It looks for patterns that have appeared more than once or are useful after the current task.
Command Claude Code
A deep-analysis command for difficult implementation, bug, and design problems, using Fable 5. It compares several possible approaches, selects one, and examines edge cases and next steps.
Command Claude Code
A documentation command that checks project code against AGENTS.md, INDEX.md, and work documents, then updates descriptions that no longer match.
Command Claude Code
A command that selects lasting design decisions from private completed work notes and prepares them as public records in the contributing directory. It removes duplicates and checks for secrets, personal data, and internal details before promotion.
Command Claude Code
A command for planning and writing software tests, including tests for normal cases, edge cases, errors, and performance. It also checks that tests really verify behavior and are not fake or unreliable tests.
Command Claude Code
A guided command for preparing an npm release, including version selection, changeset checks, compatibility review, and a release pull request. Changesets are files that describe package changes and help determine the next version.
Command Claude Code
A command that creates a dated work-plan document from a topic, including goals, requirements, items outside the task, test cases, and open questions.
Command Claude Code
A command that writes a VitePress documentation page, with VitePress being a tool for building documentation websites. It requires matching Korean and English versions and checks the project's documentation settings first.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing pr-merge-guard.sh, gh-language-gate.sh, adversarial-review-gate.sh and issue-parent-gate.sh via bash (4 commands). From jo-duchan/tapflow.
Hook Claude Code
Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing docs-aitells-reminder.sh via bash. From jo-duchan/tapflow.
Hook Claude Code
Runs when the agent finishes a response, executing docs-aitells-gate.sh via bash. From jo-duchan/tapflow.
Settings file Claude Code
Agent settings declaring 3 hook events (PreToolUse, PostToolUse, Stop).
Instructions file CodexOpenCode
Instructions for jo-duchan/tapflow, covering tapflow — agents.md (common rules), what, core value, two testing modes and why.
Instructions file
Instructions for jo-duchan/tapflow, a project described as: Self-hosted iOS & Android simulator streaming for the whole team.