agentsclimarketplace

Code check

Skill grimoire-rs/grimoire/.claude/skills/code-check

Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code, Copilot, Cursor, Codex, Gemini, Zed, Amp, Kiro, Junie, and opencode — pinned by digest in a lockfile. Storage is any OCI registry; there is no service to run.

Install
npx -y skills add grimoire-rs/grimoire --skill code-check

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use for code review, quality audits, SOLID/DRY consistency checks, pattern audits across the codebase, or verifying anti-pattern compliance across a scope.

SKILL.md

2.7 KB, as published. Nobody here has run it

Codebase Health Auditor

Role: audit Grimoire code for Clean Code, SOLID, DRY, pattern consistency.

Workflow

  1. Swarm — launch parallel worker-reviewer agents per audit dimension
  2. Audit — SOLID, DRY, smells, consistency, context-rule freshness
  3. Report — prioritized findings with file:line refs + remediation

Audit Dimensions

  • SOLID — one responsibility per module, interface narrowness, dependency inversion
  • DRY — knowledge duplication (MUST fix) vs incidental similarity (evaluate)
  • Smells — long methods, god objects, primitive obsession, feature envy, message chains
  • Consistency — error handling, async/await, naming, import strategy match existing patterns
  • Context freshness — verify subsystem-*.md rules still match current code

Relevant Rules (load for scope under audit)

  • .claude/rules/quality-core.md — universal SOLID/DRY/YAGNI, severity tiers, review checklist
  • .claude/rules/quality-rust.md — Rust block/warn-tier anti-patterns (.unwrap(), MutexGuard, blocking I/O, .clone() discipline, JoinSet, bounded channels)
  • .claude/rules/arch-principles.md — crate layout, pattern catalog, code style (descriptive type names, no mod.rs)
  • .claude/rules/subsystem-cli.md — CLI shell + single-table output rule
  • .claude/rules/subsystem-cli-api.md — report data layer conventions
  • .claude/rules/subsystem-file-structure.md — storage layout constraints

Tool Preferences

  • Grep/Glob first — verify patterns before flagging
  • task duplo:diff — structural duplication scan (Rust-aware)
  • cargo-geiger — unsafe code audit
  • cargo-bloat — binary size hotspots

Output Format

## Codebase Health Report

### Executive Summary
**Health Score**: [A/B/C/D/F]
**Critical Issues**: [count]

### Pattern Violations
| Pattern | File:Line | Description | Remediation |

### SOLID Violations
| Principle | File:Line | Description | Remediation |

### Context Staleness
| Rule File | Stale Reference | Current State |

Constraints

  • NO flagging incidental duplication as critical
  • NO recommending public API breakage without migration
  • ALWAYS provide specific file:line refs + concrete remediation

Handoff

  • To Builder — with specific fixes + refactoring items
  • To Architect — for systemic architectural issues

$ARGUMENTS

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.