code-quality agents

Calvin-LLC/agentic-hardening-skill

Agent

OWASP Top 10:2025 appsec and supply-chain assessment with Source→Sink evidence. AI feature section only when recon.ai is true.

Calvin-LLC/agentic-hardening-skill

Agent

Discovers tests, coverage config, and gaps. Executes nothing at T0. Higher tiers require host sandbox attestation in the contract.

nikolaypaskov/claudeconf-plugin

Agent

Check a claudeconf-generated harness against its RECORDED constitution profile — advisory, evidence-driven, read-only. Use when the user asks to check, diagnose, or "doctor" their harness, verify pins/wiring/drift, see whether branch protection matches the enforcement checklist, or whether a profile upgrade is…

jx-hxxx/hi-vibe

Agent

Clean-context design reviewer. Reviews just-written code changes with zero memory of writing them — catches half-finished changes and cross-file drift (a file updated but the file pointing at it left stale), then over-engineering, scope creep, and simpler alternatives: the judgment calls hooks and checklists cannot…

jx-hxxx/hi-vibe

Agent

An evidence checker for possible duplicate-code findings from a repository scan. It opens the actual code and decides whether each scanner result is a real duplicate, a false alarm, or uncertain.

Sh3rd3n/megazord

Agent

Execute a single plan file with atomic commits per task.

Sh3rd3n/megazord

Agent

Analyze an existing codebase for brownfield project support.

Sh3rd3n/megazord

Agent

Two-stage code review for spec compliance and code quality.

airmcp-com/mcp-standards

Agent Claude Code

Matrix of agent capabilities and their specializations.

airmcp-com/mcp-standards

Agent Claude Code

Guide to spawning agents with Claude Code's Task tool.

airmcp-com/mcp-standards

Agent Claude Code

Complete guide to all 54 available agent types in Claude Flow.

Piyush8296/claude-workspace

Agent Claude Code

Audit frontend code for WCAG 2.1 AA compliance. Use when building UI components, before launch, or when accessibility issues are reported. Checks semantic HTML, keyboard navigation, ARIA, color contrast, and screen reader compatibility.

Piyush8296/claude-workspace

Agent Claude Code

MUST BE USED PROACTIVELY after writing or modifying any code. Reviews against project standards, TypeScript strict mode, React patterns, accessibility, and performance. Catches anti-patterns before they ship.

Piyush8296/claude-workspace

Agent Claude Code

Plan safe, incremental refactoring strategies. Use when code needs restructuring, patterns need updating, or technical debt needs addressing. Creates a step-by-step migration plan with rollback points.

thomas-powers-jr/cadence

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

thomas-powers-jr/cadence

Agent

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

thomas-powers-jr/cadence

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

Mnemoclaw/chimera

Agent

You are a Structural Architect, not a summarizer. You implement meritocratic arbitrage from the PRISM framework.

Mnemoclaw/chimera

Agent

You are one of N parallel perspective agents in the PRISM system (Prospective Refinement through Intelligent Synthesis and Multiplicity).

Mnemoclaw/chimera

Agent

You are an exploration agent inspired by Physarum polycephalum (slime mold). Your biological principle: explore ALL viable paths before any pruning occurs.

assist-software/claude-code-repository

Agent

Reads a codebase's READMEs, feature docs, configuration, and surrounding business logic to build a concise project-context brief used when authoring new prompts. Read-only.

assist-software/claude-code-repository

Agent

Scans a codebase for LLM usage, extracts prompt inventory and project conventions in a single pass. Used by /prompt-init to populate OVERVIEW.md and rules/project-conventions.md. Read-only.

assist-software/claude-code-repository

Agent

Sweeps a codebase (any language) to locate every LLM prompt and prompt template, returning a structured inventory with a confidence score per hit. Use as the first stage of an audit. Read-only.

zircote-plugins/refactor

Agent

Code architecture analyst, optimization planner, and feature architecture designer. Reviews code from a design perspective, identifies architectural improvements, creates prioritized optimization plans, performs final quality assessments, and designs comprehensive implementation blueprints for new features.