Agent skill
pre-modification-check
Use before modifying, refactoring, or deleting files in a codebase that has Repowise indexed (indicated by a .repowise/ directory). Activates when Claude is about to edit code, especially shared utilities, core modules, or files the user didn't explicitly mention. Helps assess impact and avoid breaking things.
Install this agent skill to your Project
npx add-skill https://github.com/repowise-dev/repowise/tree/main/plugins/claude-code/skills/pre-modification
SKILL.md
Pre-Modification Check with Repowise
Before modifying files in a Repowise-indexed codebase, assess the impact.
Before editing a file
Call get_risk(targets=["path/to/file.py"]) to understand:
- Hotspot status — is this a high-churn file? Extra care needed.
- Dependents — what other files/modules depend on this? How wide is the blast radius?
- Co-change partners — what files typically change together with this one? You may need to update them too.
- Ownership — who owns this code? Relevant for PR review routing.
- Bus factor — if only 1 person owns this, changes need extra review.
When modifying multiple files
Batch all targets into one call: get_risk(targets=["file1.py", "file2.py", "module/"]).
When to warn the user
If get_risk shows:
- Hotspot score above 90th percentile — mention this is a frequently-changed, high-risk file
- More than 10 dependents — list the top dependents; API changes here will break consumers
- Bus factor of 1 — note that a single person maintains this code
- Risk type is "bug-prone" or "high-coupling" — flag explicitly before making changes
Before refactoring or moving code
Call get_context(targets=["file.py"]) first to understand the full context: what uses this file, what decisions govern it, and why it's structured this way. This prevents accidentally violating architectural decisions.
Error handling
If get_risk returns a tool error, the MCP server may not be running. Proceed with the modification but note that risk assessment was unavailable.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
codebase-exploration
Use when exploring, understanding, or answering questions about a codebase that has Repowise indexed (indicated by a .repowise/ directory in the project root). Activates for questions like "how does X work", "explain the architecture", "where is Y implemented", "what does this module do", or any task requiring understanding of codebase structure before diving into source files.
dead-code-cleanup
Use when the user asks about cleanup, removing unused code, refactoring, reducing bundle size, or identifying dead code in a Repowise-indexed codebase (.repowise/ directory exists). Also activates when discussing technical debt, code hygiene, or repository maintenance.
architectural-decisions
Use when encountering questions about WHY code is built a certain way, when about to make architectural changes (new patterns, restructuring, choosing between approaches), or when the user asks about design rationale in a Repowise-indexed codebase (.repowise/ directory exists). Also activates when commit messages or code comments contain decision signals like "WHY:", "DECISION:", "TRADEOFF:", "ADR:".
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Didn't find tool you were looking for?