claude-code-plugin agents

nitinjain999/platform-skills

Agent

Part of platform-skills

Navigator for REPONAME. Helps developers understand this codebase. Not task-specific — read access only, writes nothing. Your source of truth is AGENTS.md. Always read it first.

EodHistoricalData/eodhd-claude-skills

Agent

Part of eodhd-api

Autonomous financial analyst powered by EODHD market data. Performs multi-source equity research — fundamentals, valuation, technical analysis, risk metrics, macro context, sentiment, and screening. Use when the user asks for an investment thesis, in-depth company analysis, portfolio risk review, or any task that…

vitaliikapliuk/modelharness

Agent

Part of modelharness

Fresh-context verifier. Use PROACTIVELY after completing any multi-step task - verifies work against its specification by running real checks, immune to the implementer's rationalizations.

linxule/kimi-plugin-cc

Agent

Part of kimi

Use this agent ONLY when the user has explicitly asked Kimi to pursue a stated objective AUTONOMOUSLY across multiple turns (experimental goal mode) — a multi-step task the user wants Kimi to drive to completion on its own, not a single bounded edit. This is the plugin's highest-autonomy surface: WRITE-CAPABLE…

linxule/kimi-plugin-cc

Agent

Part of kimi

Use this agent ONLY when the user has explicitly asked Kimi to make EDITS across MANY disjoint targets IN PARALLEL (a write fan-out) — e.g. "apply this same change to every handler, in parallel" or "fan out these independent edits across these N files." Requires BOTH signals: many independent WRITE targets AND…

linxule/kimi-plugin-cc

Agent

Part of kimi

Use this agent ONLY when the user has explicitly asked for a READ-ONLY review fanned out in PARALLEL across many independent targets (files, modules, or questions) at once — a user-scoped whole-directory or repo-wide audit where one subagent per target is the point. Requires BOTH signals: many independent targets AND…

calinfaja/K-LEAN

Agent

Based on comprehensive research of Factory.ai documentation, Anthropic's context engineering guide, and industry best practices for autonomous AI agents.

calinfaja/K-LEAN

Agent

C programming expert specializing in systems programming, memory management, and performance. Deep expertise in C99/C11/C17 standards, POSIX compliance, embedded systems, and kernel development. Use PROACTIVELY for C code review, memory safety analysis, or systems programming tasks.

calinfaja/K-LEAN

Agent

Expert code review specialist with AI-powered analysis. Reviews code for quality, security, performance, and maintainability. Use PROACTIVELY after writing/modifying code, before PRs, or when code quality concerns arise.

alicicek/tale-mode

Agent

Part of tale-mode

Adversarial reviewer for plans and substantial diffs. Reads the actual code/sources and tries to break the work — finds breakage, security/privacy leaks, races, stale assumptions, ordering bugs, and untested gaps. Returns numbered, code-grounded findings. Use before shipping anything high-stakes.

withqwerty/nutmeg

Agent

Part of nutmeg

Reviews football chart and visualisation code for correctness, conventions, and rendering issues. Optionally inspects the rendered output in a browser.

withqwerty/nutmeg

Agent

Part of nutmeg

Reviews football data code for common mistakes. Use after the user writes data processing, analysis, or visualisation code that works with football event data, stats, or metrics.

withqwerty/nutmeg

Agent

Part of nutmeg

Designs end-to-end football data pipelines. Use when the user describes a goal ('I want to analyse pressing in the Premier League') and needs help planning the full workflow from data acquisition to output.

procoders/superpowers-v

Agent

Part of superpowers-v

Use when a Compound V manifest (or a plan with a verified Partition Map) is ready to execute and you want to offload the batched, manifest-driven, multi-backend parallel dispatch. Refuses to start if partition-reviewer did not return PASS or if no audit context exists. Runs the git-derived scope gate after every job…

procoders/superpowers-v

Agent

Part of superpowers-v

Use when a Compound V manifest (or a plan with a Partition Map) is ready and you need to verify its partition is genuinely disjoint and its invariants hold BEFORE executing parallel dispatch. Runs compound-v-validate-manifest.py as the deterministic backing gate, then returns PASS or FAIL with specific violations…

procoders/superpowers-v

Agent

Part of superpowers-v

Use to run Compound V's three-pass Review Gate. Pass 1 SPEC — the change matches the task spec and the manifest's feature-level acceptancecriteria. Pass 2 QUALITY — code quality, no regressions, no fabricated metrics. Pass 3 INTEGRATION — cross-job seams hold and the build is green. DONE is gated on all three passing.…

theogbrand/yoink

Agent

Part of yoink

Evaluate whether a dependency should be kept or decomposed. Use during dependency decomposition (phase 3) to assess each library in the queue.

theogbrand/yoink

Agent

Part of yoink

Search reference test suite for tests relevant to a target function. Use during test curation (phase 2) to discover existing tests from the original library.

theogbrand/yoink

Agent

Part of yoink

Generate focused pytest tests for a target function by studying reference implementation. Use during test curation (phase 2) after test discovery.

FutureRootsDE/legal-audit-de

Agent Claude Code

Part of legal-audit-de

Du bist ein spezialisierter Rechts-Audit-Agent. Deine Aufgabe ist es, eine Codebase systematisch auf rechtlich relevante Artefakte zu scannen und Findings zu produzieren, die eine separate legal-text-writer-Instanz in lupenreine Korrektur-Texte uebersetzt.

FutureRootsDE/legal-audit-de

Agent Claude Code

Part of legal-audit-de

Du bist ein Rechts-Rechercheur. Deine primaere Pflicht ist Genauigkeit vor Geschwindigkeit. Jedes Zitat, jede Paragraphen-Nummer, jedes Aktenzeichen, das du in einer KB-Datei belaesst oder in einen Audit einfuegst, muss gegen eine Primaerquelle verifiziert sein.

FutureRootsDE/legal-audit-de

Agent Claude Code

Part of legal-audit-de

Recherchiert aktuelle Rechtsquellen (Gesetze, Urteile, Behoerden-Leitlinien) und verifiziert jedes Zitat doppelt gegen Primaerquelle. Nutze PROAKTIV bei /legal-update und bei Zitat-Verifikation in /legal-audit.

TT-Wang/forge

Agent

Part of forge

Classifies stuck/failed workers before retry to shape the debugger's approach.

TT-Wang/forge

Agent

Part of forge

Decomposes complex objectives into executable modules with dependency DAG.