Agents

oaustegard/claude-skills

Agent Claude Code

Haiku 5.5 decision sampler for the deciding-with-confidence skill. Answers one sample prompt from decide.py emit --agent decider with a probability per option, as JSON, with no tools and no prose. Dispatch several in parallel, then pool the replies with decide.py aggregate; one reply alone is not a calibrated answer.

gpsaggese/helpers

Agent Claude Code

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.

AndreevED/1c-ai-feature-dev-workflow

Agent Claude Code

An architecture-planning agent for 1C business software, a platform used to build enterprise applications. It studies an existing 1C codebase and produces a detailed design and implementation plan for changes.

DebugBase/glance

Agent Claude Code

Tests web applications end-to-end using Glance browser MCP. Navigates pages, fills forms, clicks buttons, takes screenshots, runs assertions, and reports bugs. Use when you want to verify an app works correctly — login flows, forms, navigation, responsiveness — with real browser interaction.

shunk031/dotfiles

Agent Claude Code

GitHub and pull request workflow agent.

nwiizo/ccswarm

Agent Claude Code

Client-side features, accessibility, and browser tests in target projects and examples.

artemiimillier/bulletproof

Agent Claude Code

Reviews code for bugs, security, performance, and spec compliance. Run in fresh context without implementation bias.

NEWBIE0413/gemini-gpt-hybrid

Agent Claude Code

AGGRESSIVE hybrid agent that delegates code generation and modification directly to Gemini and GPT for rapid development and automation.

cloudnative-co/claude-code-starter-kit

Agent Claude Code

Software architecture specialist for major design decisions, system boundaries, scalability, and migration strategy. Use for complex features or refactors where trade-offs must be explicit.

arbiterForge/codeArbiter

Agent Claude Code

INTERNAL SMARTS analyst dispatched by the decision-variance skill. Produces a SMARTS analysis and recommendation for one (artifact-position, scaffold-evidence) pair. Never decides — the user decides. Never dispatch directly.

Weebapp003/tradingview-mcp

Agent Claude Code

Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.

ahpxex/open-dashboard

Agent Claude Code

Use this agent for architectural decisions, feature design, code review, or refactoring in this TanStack Start back-office / dashboard starter ("中台" template). It knows the resource pattern, the Repository data layer, the page archetypes, and the ALWAYS/NEVER conventions, and it designs changes that stay portable and…

hamzafarooq/claude-code-starter

Agent Claude Code

Fetch and extract a single competitor's pricing tiers. Tries WebFetch first (cheap); falls back to Playwright browser automation only when the page is JS-rendered or pricing is hidden behind interactions. Spawned by the competitor-research skill — one instance per competitor, run in parallel.

dmae97/omk

Agent Claude Code

A deranged comment-hater that savors deletion and condemns workaround code.

yezannnnn/agentGroup

Agent Claude Code

Use this agent when you need to run tests and analyze their results. This agent specializes in executing tests using the optimized test runner script, capturing comprehensive logs, and then performing deep analysis to surface key issues, failures, and actionable insights. The agent should be invoked after code changes…

vigolium/piolium

Agent Claude Code

Phase 1 intelligence gathering agent that collects security advisories (CVE, GHSA, OSV) with adaptive time expansion, builds architecture inventory, compiles a general component inventory (SBOM) of every software component the target relies on, and synthesizes vulnerability pattern analysis (recurring components, bug…

Ovid/paad

Agent Claude Code

Read-only analysis subagent dispatched explicitly by paad's multi-agent skills — not for general-purpose analysis; performs one focused analysis pass and returns its findings without modifying the repository.

flonat/flonat-research

Agent Claude Code

Adversarial auditor for LaTeX papers. Read-only with respect to project files (paper, bib, code, data); writes its own report at reviews/ /paper-critic/ .md plus a findings.json sidecar. Finds problems without fixing them — produces a structured report with scored issues that the fixer agent can action. Assumes the…

AgriciDaniel/seo-os

Agent Claude Code

Compose the ULTIMATE BEAST plan for a marketing-brain client vault. Reads the populated vault (audits, keyword targets, cannibalization ledger, competitors, business-type overlay), the keywords XLSX summary, the PAA digest, and the FLOW + beast-plan-prompt references. Writes wiki/deliverables/ULTIMATE BEAST Plan.md…

AnkitClassicVision/Claude-Code-Deep-Research

Agent Claude Code

Use this agent on the draft report during Phase 5 of deep research, after synthesis and before the gates. Mandatory for Deep and Exhaustive tiers and for any decision-tier claim.

alfredolopez80/multi-agent-ralph-loop

Agent Claude Code

You are an AI Output & Code Review Super-Auditor.

HsienW/chat-gun-react-agent

Agent Claude Code

MUST BE USED for independent, read-only architecture, security, OpenSpec traceability, cross-layer contract, LangGraph, Tool and MCP review.

minorun365/my-claude-code-settings

Agent Claude Code

A testing and debugging assistant for web applications, using browser inspection, automated browser tests, local runs, and application logs.

selmakcby/claude-agents-skills

Agent Claude Code

Use PROACTIVELY immediately after builder produces code. Double-role agent that checks BOTH code quality AND security before commit. Blocks merge on CRITICAL issues.