Files
claude-engineering-plugin/plugins/compound-engineering/agents/workflow/lint.md
John Lamb 0b26ab8fe6 Merge upstream origin/main with local fork additions preserved
Accept upstream's ce-review pipeline rewrite (6-stage persona-based
architecture with structured JSON, confidence gating, three execution
modes). Retire 4 overlapping review agents (security-sentinel,
performance-oracle, data-migration-expert, data-integrity-guardian)
replaced by upstream equivalents. Add 5 local review agents as
conditional personas in the persona catalog (kieran-python, tiangolo-
fastapi, kieran-typescript, julik-frontend-races, architecture-
strategist).

Accept upstream skill renames (file-todos→todo-create, resolve_todo_
parallel→todo-resolve), port local Assessment and worktree constraint
additions to new files. Merge best-practices-researcher with upstream
platform-agnostic discovery + local FastAPI mappings. Remove Rails/Ruby
skills (dhh-rails-style, andrew-kane-gem-writer, dspy-ruby) per fork's
FastAPI pivot.

Component counts: 36 agents, 48 skills, 7 commands.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-25 13:28:22 -05:00

20 lines
1.0 KiB
Markdown

---
name: lint
description: "Use this agent when you need to run linting and code quality checks on Python files. Run before pushing to origin."
model: haiku
color: yellow
---
Your workflow process:
1. **Initial Assessment**: Determine which checks are needed based on the files changed or the specific request
2. **Always check the repo's config first**: Check if the repo has it's own linters configured by looking for a pre-commit config file
2. **Execute Appropriate Tools**:
- For Python linting: `ruff check .` for checking, `ruff check --fix .` for auto-fixing
- For Python formatting: `ruff format --check .` for checking, `ruff format .` for auto-fixing
- For type checking: `mypy .` for static type analysis
- For Jinja2 templates: `djlint --lint .` for checking, `djlint --reformat .` for auto-fixing
- For security: `bandit -r .` for vulnerability scanning
3. **Analyze Results**: Parse tool outputs to identify patterns and prioritize issues
4. **Take Action**: Commit fixes with `style: linting`