PreToolUse
01Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing guard-bash.sh via bash. From Kimyongari/harness-factory.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing guard-bash.sh via bash. From Kimyongari/harness-factory.
Hook Claude Code
Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing pre-commit.sh via bash. From Kimyongari/harness-factory.
Hook Claude Code
Runs when the agent finishes a response, executing verify.sh via bash. From Kimyongari/harness-factory.
Settings file Claude Code
Agent settings declaring 3 hook events (PreToolUse, PostToolUse, Stop).
Skill Claude CodeCodex
A set of rules for writing, changing, testing, and checking code in a project.
Skill Claude CodeCodex
Writing rules for README files, technical documents, design documents, change summaries, pull-request descriptions, and user-facing prose, with Korean as the default language.
Skill Claude CodeCodex
A set of rules for using Git and GitHub in software projects. Git tracks code changes, while GitHub hosts repositories and supports collaboration through branches, issues, and pull requests.
Skill Claude CodeCodex
A set of rules for searching the web, checking facts, and citing sources. It covers current information, software documentation, and safe handling of instructions found online.
Instructions file
Project instructions for Harness Factory, a Python 3.13 service that sets up coding-agent harnesses from a questionnaire. They describe its commands, runtime checks, and development boundaries.
Skill Claude CodeCodex
Use when asked to review code. Triggers - "look at this PR", "review this diff", "safe to merge?", change inspection. Input is a diff/branch/PR; output is a severity-ranked list of findings at file:line. If the job is to change code, use development.
Skill Claude CodeCodex
Use when hunting the cause of a bug, error, or failing test — and before proposing any fix. Triggers - "why doesn't this work", stack traces, flaky failures, regressions ("worked yesterday"). Output is reproduce → root cause → minimal fix → regression test. If you already know the cause and just need the fix, use…
Skill Claude CodeCodex
Token-saving mode for everyday lightweight work. Use for one-line fixes, typo/config-value changes, quick questions ("what does this function do?"), throwaway scripts, and anything that ends inside a single file. Output is a minimal diff and a short report. For multi-file, design, or new-feature work, switch to the…