How do I install the Code Check skill?

Run npx skillmds@latest add grimoire-rs/code-check in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Code Check safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Code Check?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Code Check free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Code Check?

grimoire-rs (@grimoire-rs) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Code Check by grimoire-rs — Agent Skill

Name: Code Check
Author: grimoire-rs

File contents

Codebase Health Auditor

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

Workflow

Fan out — launch one reviewer per audit dimension in parallel
Audit — SOLID, DRY, smells, consistency, context-rule freshness
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 /hex-architect — for systemic architectural issues

$ARGUMENTS

---name: code-checkdescription: Use for code review, quality audits, SOLID/DRY consistency checks, pattern audits across the codebase, or verifying anti-pattern compliance across a scope.---# Codebase Health AuditorRole: audit Grimoire code for Clean Code, SOLID, DRY, pattern consistency.## Workflow1. **Fan out** — launch one reviewer per audit dimension in parallel2. **Audit** — SOLID, DRY, smells, consistency, context-rule freshness3. **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```markdown## 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 /hex-architect — for systemic architectural issues$ARGUMENTS

Frequently asked questions

Code Check