19,479 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
ThomasVitale/agents-skills-oci-artifacts-spec
Skill Claude CodeCodex
A skill for managing pull requests in Forgejo repositories using the forgejo-cli. Supports creating, listing, viewing, merging, closing, and commenting on PRs.
Skill Claude CodeCodex
Use when generating or reviewing Java backend code (Service/Controller/Mapper) that touches a database, Redis, MQ, RPC, SMS/email, or file writes. Applies a 5-gate checklist (requirements review, concurrency safety, transaction boundaries, null-safety, security) distilled from real production incidents, so…
Skill Claude Code
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Skill Claude CodeCodex
Review and score Drupal code across security, correctness, efficiency, complexity, duplication, testing, and documentation, producing a weighted score and a merge verdict. Use this skill whenever the user wants Drupal code reviewed, scored, or checked before merging - including custom modules, themes, plugins…
Plugin Claude Code
Bundles 13 skills · 1,537 tokens together
Architecture-aware engineering principles framework for Claude Code. Provides systematic, tiered workflows for bug fixes, new features, refactoring, code review, test writing, requirements refinement, debugging, shipping, sprint planning, migrations, and security audits.
mnapoli/skill-address-pr-review
Skill Claude Code
Look at the pull request review comments and address any issues raised.
Skill Claude CodeCodex
Find deepening opportunities in a codebase, informed by the domain language in .context/ and the decisions in .context/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Plugin Claude Code
Bundles 15 skills, 7 agents, 1 MCP server · 639 tokens together
A dev pipeline for Claude Code that will not call work done until tests, lint and a security audit all exit zero. Seven specialists run it, for 1.1k tokens of always-on context.
whitequeen306/code-cortex-loop
Cursor rule Cursor needs its repo
CodeCortexLoop v2.2 workflow — presets, health scores, suppression, re-verify, CI output, baseline, dashboard, learning loop. Apply when running /cortexloop.
Skill Claude CodeCodex
Systematic code review checklist.
openonion/connectonion-claude-plugin
Plugin Claude Code
Bundles 7 skills, 5 commands · 167 tokens together
ConnectOnion framework development plugin - code review and agent builder following ConnectOnion philosophy. Join our community: https://discord.gg/4xfD9k8AUF.
MCP server Claude CodeCodexCursor +2
Check whether a coding agent's changes stayed inside the scope it was given. Runs locally from the mergewarden-mcp npm package.
Plugin Claude Code
Bundles 16 skills, 1 agent · 1,317 tokens together
ESP for AI Coding — Agent skills on the philosophy of software design, grounded in decades of engineering experience.
costrict-plugins-repo/multica-ai-karpathy-skills-andrej-karpathy-skills
Cursor rule Cursor
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Skill Claude CodeCodex
CVE-oriented multi-agent code audit system. Use when user provides a git repository URL for vulnerability discovery with the goal of submitting CVEs. This skill orchestrates subagents to find exploitable vulnerabilities (RCE, SQLi, Auth Bypass, etc.), write weaponized POCs, and generate CVE-ready reports. ALWAYS use…
Plugin Claude Code
Bundles 2 skills · 90 tokens together
Adversarial multi-model code review. Dual Optimizer/Skeptic agents (Sonnet + Opus) challenge each other's findings. Pulls GitHub PR feedback, reviews against project conventions, auto-fixes consensus issues, presents disputes for author decision.
Plugin Claude Code
Slop-mop quality gates as a Claude skill — directed remediation for AI-assisted codebases.
FarzamHabibi/pre-production-checklist
Skill Claude CodeCodex
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
Cursor rule Cursor
Hunch engineering memory — consult the hunch MCP tools before editing.
Plugin Claude Code
Bundles 28 skills · 2,381 tokens together
The most comprehensive agent skill set for real Rust: ownership over clone and unwrap, errors and APIs that survive review, async and unsafe done right, plus disciplined porting into Rust.
Skill Codex
Delegate bounded software-engineering subtasks from Codex to an explicitly selected Pi provider/model pair. Use when a supervising agent would benefit from an independent architecture opinion, broad read-only code analysis, parallel debugging hypotheses, code review, test or documentation drafting, or a candidate…
Skill Claude Code
Tiered adversarial review orchestrator for a working tree, branch diff, pull request, or plan/markdown artifact before it lands on main — a staged reviewer panel (spec, quality, security, performance, docs), root-cause analysis, and a cross-model adversarial pass (codex, medium and up) scale with diff size via tier…
Skill Claude CodeCodex
Use when you run in a Talyn thread, a conversation with no repository. Explains how to plan work across repositories, how to brief and start a session on each repository with talyncreatesession, why to end your turn instead of polling (Talyn wakes you when a session finishes, opens a pull request or needs an answer)…
Skill Claude CodeCodex
Interpret and act on a moire finding. Use when moire check or moire verify reports a CONFLICT or BROKEN result against another agent's worktree, or when deciding how to respond to an overlap with concurrent in-flight work.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: