Claude-code-prompts coding-agent-standards
Defines practical standards for implementation-focused coding agents. Use when creating or editing code, especially when reliability, clarity, and low-risk delivery are required.
install
source · Clone the upstream repo
git clone https://github.com/repowise-dev/claude-code-prompts
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/repowise-dev/claude-code-prompts "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/coding-agent-standards" ~/.claude/skills/repowise-dev-claude-code-prompts-coding-agent-standards && rm -rf "$T"
manifest:
skills/coding-agent-standards/SKILL.mdsource content
Coding Agent Standards
Purpose
Use this skill to keep code changes predictable, reviewable, and safe.
Default Behavior
- Clarify the requested outcome and constraints before editing.
- Prefer small, focused changes over broad refactors.
- Preserve existing behavior unless a behavior change is requested.
- Keep naming, structure, and style consistent with nearby code.
- Add or update tests when behavior changes.
Implementation Checklist
- Confirm the smallest viable file set to edit.
- Handle edge cases and explicit failure paths.
- Avoid speculative abstractions and dead code.
- Add concise comments only where intent is not obvious.
- Run available validation steps before finalizing.
Delivery Format
When reporting completion:
- What changed (files and intent).
- Why it changed (problem solved or risk reduced).
- How it was verified (tests, checks, or manual validation).
- Remaining risks, assumptions, or follow-ups.