Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
mjendza/entra-id-permissions-mcp
Agent Claude Code
Lightweight variant of entra-sp-architect that needs NO Terraform MCP / Docker. Use when the user wants to create an Entra ID (Azure AD) service principal / app registration with a specific set of Microsoft Graph permissions expressed as Terraform, but does not have the Docker-based terraform MCP running. Resolves…
Agent Claude Code
Maintains ClawMem memory health — lifecycle triage (pin/snooze/forget), retrieval health checks, dedup sweeps, graph rebuilds, index hygiene. Use when "curate memory", "memory maintenance", "run curator", or after long productive sessions.
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
Agent Claude Code
Product Requirements Document builder with guided Q&A and references.
Agent Claude Code needs its repo
Gathers third-party Reception signal for ONE existing LibrAIum entry and writes (or refreshes) its ## Reception section in house style — sourced, attributive bullets synthesized from the GitHub dossier, with the provenance stamp and the receptiongathered date updated and the entry ticked in the coverage checklist.…
Agent Claude Code
Review code against clean-code conventions and an OWASP security checklist.
BluePandaNYC/tradingview-mcp-jackson-
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
Agent Claude Code
Cache-miss web research executor for web-research-mcp. Use when checkreference/ resolvereference/searchreference returned a miss or stale result for a tracked tech and someone needs to run WebSearch/WebFetch, summarize the findings, and save them via saveresearch. Single-shot mechanical extraction — do NOT use for…
kylepk-boop/tradingview-mcp-jackson
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
Agent Claude Code
Adaptive specification coordinator. Inspects context, asks only blocking questions, selects direct, specialist-assisted, or full-council planning, and writes a dependency-aware spec before stopping for approval.
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
Agent Claude Code
Claude Fable as advisor/orchestrator. Plans and reviews; delegates implementation to Grok via MCP (executetask / reviewtask). Use for multi-step features, refactors, and hard design work.
Agent Claude Code
Takes review findings from a reviewer agent and inserts them as pending review threads into the Emacs pr-review buffer. Does NOT analyze, does NOT publish — just inserts.
Agent Claude Code
OCR pipeline development, backend integration, and table reconstruction.
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
Agent Claude Code
Deep research on a specific tool, library, framework, protocol, or technical topic, using Exa web search as the primary source. Use when the question needs current external documentation rather than the local codebase — API surfaces, version differences, release notes, migration paths, competing approaches, "how do…
Agent Claude Code
Quickbase specialist for this toolkit. Use for anything Quickbase-specific — writing/debugging formulas and formula fields (Text/Numeric/Date/Checkbox/Rich Text), the built-in function catalog, date/duration arithmetic, rich-text HTML fields and Formula-URL action buttons, building code pages (in-app HTML/JS widgets)…
mdtasleem2002-omar/tradingview-mcp
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
lexasanych1984-ux/tradingview-mcp
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
federicopigozzi/tradingview-mcp
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
yuzu-octopus/Codebreaker_Solver
Agent Claude Code
Competitive programming solver subagent for codebreaker.xyz — reads /tmp/stmt .txt, writes solve/ .cpp with the repo template, tests with coderunner, reports. Also serves as fixer when given a judge verdict. Runs on the free opencode-zen/deepseek-v4-flash-free model.
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
Agent Claude Code
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
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: