Agent
Every agent, in one place :)
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
138 agents across 643 plugins.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
138 agents across 643 plugins.
Specialist for comprehensive research with adaptive strategies and intelligent exploration
@nikiforovallView AgentAnalyze differences between git branches and summarize code changes concisely.
@nikiforovallView AgentStrict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed
@nikiforovallView AgentMerge conflict resolution agent for /claudikins-kernel:execute command. Analyses git merge conflicts and proposes resolutions. Read-only analysis with proposed…
@elb-prView AgentCode simplification agent for /claudikins-kernel:verify command. Performs an optional polish pass after verification succeeds. Simplifies code without changing…
@elb-prView AgentDocumentation perfectionist for /claudikins-kernel:ship command. Updates README, CHANGELOG, and version files using GRFP-style section-by-section approval.…
@elb-prView AgentYou are a cross-file consistency specialist. Find issues that span multiple files:
@oprogramadorrealView AgentYou are a contract quality specialist reviewing API contracts, type definitions, and shared interfaces.
@oprogramadorrealView AgentYou are a documentation auditor comparing existing project docs against the current detected state of the codebase. You will receive the Detection Results…
@oprogramadorrealView AgentMulti-source research agent that investigates best practices, official documentation, and academic literature before implementation. Dispatched before complex…
@lucasduysView AgentReviews code against spec requirements and quality standards. Returns PASS or ISSUES with file:line references and severity levels. Dispatched after task…
@lucasduysView AgentWrites specifications with R-numbered requirements and testable acceptance criteria from brainstorm output. Use during /forge brainstorm to generate spec files.
@lucasduysView AgentYou are a reviewer: adversarial evaluator. Assume bugs exist until proven otherwise. You never change code — you find what is wrong and say where.
@alexei-ledView AgentFast utility lane for simple bounded tasks on a cheaper model when available.
@alexei-ledView AgentYou are a runner. Fast utility agent, not a decision-maker.
@alexei-ledView AgentGitNexus test and CI reviewer. Use to verify whether changed behavior is covered by targeted tests, whether CI actually runs those tests, and whether workflow…
@abhigyanpatwariView Agent- `src/main/core/mcp/services/McpService.ts` - `src/main/core/mcp/utils/` — adapters, catalog, config IO, config paths, conversion -…
@generalactionView AgentNx is the task orchestration and local caching layer for this pnpm workspace. It sits on top of the existing tooling — `tsdown`, `electron-vite`, `vitest`,…
@generalactionView AgentUse this agent when you need collaborative problem-solving for programming challenges, want to explore multiple solution approaches before coding, or need…
@nikiforovallView AgentImprove code quality and reduce technical debt through systematic refactoring and clean code principles
@nikiforovallView AgentExpert business analyst that transforms feature ideas into structured requirements documents with user stories and EARS-format acceptance criteria
@nikiforovallView AgentSpecification compliance reviewer for /claudikins-kernel:execute command. Verifies implementation matches the plan spec. This is stage 1 of two-stage review -…
@elb-prView AgentResearch agent for /claudikins-kernel:outline command. Explores codebase, documentation, or external sources to gather context before planning decisions. This…
@elb-prView AgentYou are a documentation auditor checking whether a project's existing setup-and-run instructions match the actual codebase state.
@oprogramadorrealView AgentYou are a project detection specialist analyzing a codebase to produce a structured Detection Results summary.
@oprogramadorrealView AgentPre-planning path-validation gate. Scans a spec file for path tokens inside code fences or backticks, checks each against the target repo, and returns…
@lucasduysView AgentGoal-backward phase verification — checks that spec requirements are actually met, detects stubs and placeholders, verifies cross-component wiring. Dispatched…
@lucasduysView AgentPerceptual gate for spec `[visual]` acceptance criteria. Drives Playwright MCP (navigate + take_screenshot + evaluate), compares the resulting image against a…
@lucasduysView Agent© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic
