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.
lucsedirae/agent_skill_library
Skill Claude CodeCodex
Apply Pragmatic Programmer principles to raise code quality during planning and multi-class generation. TRIGGER AUTOMATICALLY (without user asking) whenever: (1) entering plan mode, (2) about to generate or modify 2+ files/classes in a single task, (3) creating new services, controllers, DTOs, or model classes, (4)…
kabudu/engineering-agent-skills
Skill Codex
Apply principal-engineer rigour to implementation, architecture, reviews, validation, and releases when the user requests expert engineering judgment, Lazarus/X mode, or staff/principal standards. Also use for rigorous security, performance, reliability, or scalability scrutiny.
joelbrilliant/agentic-delivery-skills
Skill Claude CodeCodex
Use when reviewing code adversarially or building production-bound features where rigour matters more than speed. Required for code reviews ending in a verdict (PASS/HOLD), when verifying that "tests pass" actually proves a feature works end-to-end, before closing findings as non-issues, before signing off your own…
Plugin Claude Code
Bundles 2 commands · 77 tokens together
Get a second opinion from Google's Gemini on code changes, plans, documentation, architecture, and other work products. Use when you need independent validation, cross-checking critical decisions, catching blind spots, or getting multiple AI perspectives on important work.
Plugin Claude Code
Bundles 3 skills, 4 commands, 1 MCP server · 258 tokens together
Structured spec and implementation review. Spec command runs multi-angle parallel review by default; opt into iterative fix loop with --fix. Dual-engine (Claude + Codex) spec review via /reviewer:spec-dual; result review can add a second engine (built-in /code-review or any review skill, e.g. spectra-review) with -c.
Plugin Claude Code
Bundles 1 skill, 3 commands, 2 agents · 360 tokens together
Clone your team's best code reviewers. Reads their PR review history in context, extracts a persona per reviewer — what they care about, what they catch, how they sound — and runs them as a code-review panel. Personas, not rule lists.
Skill Claude CodeCodex
Structured code review workflow and security checks.
Skill Claude CodeCodex
Use for a GitHub pull request review run to inspect the exact head revision, changed files, and checks, then publish one evidence-backed managed review comment without approving or modifying the pull request.
Plugin Claude Code
Bundles 2 skills · 246 tokens together
Defense against LLM Rust failure modes: 59 categories of bugs that survive rustc, clippy, and cargo test — async cancellation, unsafe/FFI, concurrency, crypto, supply-chain, tests-that-pass-by-luck, semantic conformance, and systemic performance cost. Ships the rust-intel skill plus /rust-intel:audit, /rust-intel:fix.
Plugin Claude Code
Bundles 5 skills, 1 command, 1 agent, 1 hook, 1 MCP server · 299 tokens together
Agent-first code understanding system. Builds a persistent world-model of your codebase with evidence-grounded facts, semantic map, behavior flows, perspectives, PR review overlay, and navigable depth via semantic zoom.
Skill Claude CodeCodex
Use when asked to proofread, review, or 校对 code or documents for correctness, logical consistency, or quality issues. Covers general code logic review (any language), plus formal-verification backends for C (ACSL contracts via Frama-C static proof and E-ACSL runtime checks), Python (icontract + CrossHair), Rust (Kani…
Agent Claude Code
Human-gated code review orchestrator that bootstraps change context, scopes hotspots, picks perspectives and depth, and merges skill-backed perspective findings into one report.
Plugin Claude Code
Bundles 4 skills · 497 tokens together
A collection of skills for software development workflows, including code review, pull-request triage, and extracting specifications from Figma designs.
BostonOrange/claude-code-framework
Agent Claude Code
Synthesizes findings from parallel reviewer agents into one consolidated report — dedupes, filters false positives, applies cross-iteration state, classifies the diff into a risk tier, and decides which sub-agents to spawn.
Skill Claude Code
Review WDK source files for JSDoc format and type-annotation conventions (JSDoc blocks, tags, type precision, imports/exports, naming).
Skill Claude CodeCodex
Fan work out to subagents safely — delegate independent packages to workers without losing ownership: draw provably disjoint lanes, write the full lane brief, order dependent tickets into waves, and keep the parent as the sole owner-gatekeeper that re-runs every gate and performs every commit and tracker write. Use…
Skill Claude CodeCodex
Explore a codebase through Cartograph v2's native RocksDB code graph: intent-aware context, exact/BM25/hybrid search, callers/callees/impact, affected tests, live source, review, freshness, and bounded index administration.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 40 tokens together
Graph-powered code intelligence for AI agents: a pre-indexed knowledge graph of your whole codebase (symbols, callers, impact/blast radius, hotspots, complexity) served over MCP. Ships the code-explorer skill and the code-explorer MCP server. Requires the code-explorer binary on PATH and an index (code-explorer analyz.
Plugin Claude Code
Bundles 51 skills, 6 commands, 9 agents · 4,571 tokens together
Reusable Claude Code skills and agents for software development workflows.
Agent Claude Code
Scoped review of an implemented change — diff first, defect checklist, short reports/review.md with PASS or FAIL. Never patches code. Use when Cortex stage is reviewing.
Plugin Claude Code
Bundles 1 skill, 1 agent, 3 hooks · 57 tokens together
Search and read code across your organisation's repositories through a Celmis server: ranked symbol search, outlines, callers, and 'do it like service X' patterns, all with a token budget and no secret values.
Skill Claude CodeCodex
Delegate coding questions, code reviews, test generation, refactoring suggestions, or second opinions to external LLMs (NVIDIA NIM, OpenRouter, Groq, DeepSeek, or a local Ollama) with zero dependencies. Use this skill whenever the user asks for another model's take, an independent review, a senior-engineer-style…
Skill Claude CodeCodex
Create or update architecture, infrastructure, deployment, swimlane, and request sequence diagrams as generated HTML pages with inline SVG and one PNG per diagram, in one fixed style with built-in layout checks. Use when the user wants to draw how an existing system, environment, pipeline, data flow, or request flow…
Skill Claude CodeCodex
Read the user's Strava activities, segments and training load through the local strava MCP server. Use when the user asks about runs, rides or swims on Strava, weekly volume, segment efforts, athlete stats, or a training review. Starts with connection status, uses synthetic demo data before OAuth, and never asks for…
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: