Instructions file CodexOpenCode
Instructions for DavidVujic/my-eca-config, covering agents.md, default skills, review instructions, five whys instructions and changes summary instructions.
Instructions file CodexOpenCode
Instructions for DavidVujic/my-eca-config, covering agents.md, default skills, review instructions, five whys instructions and changes summary instructions.
Agent
Summarize a git diff in <= 3 sentences focusing on what and why.
Agent
Review a git diff / PR with strict severity threshold.
Agent
Create a conventional commit from staged changes with a diff-derived description.
Agent
Facilitate a 5 Whys incident/ticket analysis in short dialogue.
Agent
Implement planned changes by editing code in the repo; uses functional-leaning, idiomatic style and lightweight data structures.
Agent
Create a pull request for the current feature branch.
Agent
Run linting and unit tests against the current repository, auto-discovering the correct commands.
Command
Create a conventional commit from currently staged changes.
Command
Create a pull request for the current feature branch.
Command
Run linting and unit tests against the current repository.
Command
Treat this as a code review request.
Skill Claude CodeCodex
General coding style policy for generated code: restrictive on comments, concise docstrings for modules and functions.
Skill Claude CodeCodex
Create a conventional commit from staged changes, with a diff-derived description body.
Skill Claude CodeCodex
My Eca setup with agents, instructions and skills.
Skill Claude CodeCodex
Use when a user asks what Code Health means, how to interpret scores, or why Code Health matters in daily development.
Skill Claude CodeCodex
Coding style policy for generated code: prefer idiomatic language conventions with a functional-leaning approach (pure-ish functions, composability), and prefer lightweight data structures over heavy schema/class abstractions unless clearly justified.
Skill Claude CodeCodex
Reliably obtain a non-empty unified git diff for the current branch using safe fallbacks (origin/HEAD...HEAD, origin/main...HEAD, origin/master...HEAD) and return structured JSON containing the diff and the command used.
Skill Claude CodeCodex
Use when refactoring unhealthy code and needing Code Health findings to choose small safe steps and verify improvement.
Skill Claude CodeCodex
Use when a user asks for ROI, stakeholder justification, delivery impact, or defect-risk reduction from improving Code Health in a file.
Skill Claude CodeCodex
Produce an implementation plan with a functional-leaning, idiomatic style mindset; prefers lightweight data structures over dataclasses/pydantic unless justified.
Skill Claude CodeCodex
Run linting and unit tests against the current repository, auto-discovering the correct commands from Justfile, Makefile, pyproject.toml, or package.json.
Skill Claude CodeCodex
Use when AI-generated or AI-modified changes need a Code Health gate before commit, handoff, or pull request.