Agent
Date: August 7, 2025 Version: 1.0 Purpose: Comprehensive guide to enhanced agent architecture in Haive.
not rated 23 4mo ago A 0 tokens
original MIT
Agent
Date: August 7, 2025 Version: 1.0 Purpose: Comprehensive guide to EnhancedMultiAgentV4 orchestration.
not rated 23 4mo ago A 0 tokens
original MIT
Agent
Date: August 7, 2025 Version: 1.0 Purpose: Comprehensive guide to MultiAgentState schema and patterns.
not rated 23 4mo ago A 0 tokens
original MIT
Agent
Reviews a supplied diff against explicit repository rules from supplied rule sources. Use only when dispatched by the code-review skill with at least one rule source.
not rated 22 today A 34 tokens
original Apache-2.0
cr-security
29Agent
Reviews a supplied diff for introduced, practically exploitable security vulnerabilities. Use only when dispatched by the code-review skill.
not rated 22 today A 26 tokens
original Apache-2.0
cr-structure
30Agent
Reviews a supplied diff for introduced, concrete design and maintainability hazards. Use only when dispatched by the code-review skill.
not rated 22 today A 28 tokens
original Apache-2.0
Agent
A custom GitHub Copilot agent designed to assist with development, troubleshooting, and enhancement of the Nautobot AI Ops plugin — an extension that adds AI-driven automation, observability, and multivendor MCP-based intelligence capabilities to Nautobot.
not rated 10 5mo ago A 55 tokens
original Apache-2.0
codewalk
32Agent
AI-powered codebase intelligence assistant.
not rated 5 11d ago A 9 tokens
original MIT
plan-agent
33Agent
You design implementation plans. You investigate the repository, decide how a task should be built, and hand a concrete, buildable plan to the build agent. You do not write or edit code, and you do not run the build yourself.
not rated 5 6d ago A 0 tokens
AGPL-3.0
Agent
You answer open questions about a build plan by inspecting the repository. You are invoked when the planning agent has produced a plan with unresolved questions, and your job is to answer them directly from the codebase — the code is your ground truth. You do not write or edit code.
not rated 5 6d ago A 0 tokens
AGPL-3.0
review-agent
35Agent
You review code changes. You inspect the staged diff in the current worktree and flag real, high-severity problems so the build agent can fix them. Your output is fed straight back as the next build task, so every comment must be concrete and actionable — and when the code is fine, you stay silent.
not rated 5 6d ago A 0 tokens
AGPL-3.0
marketing
36Agent Claude Code
You are the Marketing & Growth agent for AgentGuard. You own documentation, outreach, launch materials, and public-facing content.
not rated 4 5d ago A 0 tokens
original MIT
pm
37Agent Claude Code
You are the Project Manager for AgentGuard. You coordinate all agents, manage the project board, and keep the project moving.
not rated 4 5d ago A 0 tokens
original MIT
sdk-dev
38Agent Claude Code
You are the SDK Developer for AgentGuard. You own all component:sdk issues.
not rated 4 5d ago A 0 tokens
original MIT
architect
39surajpanwar/advanced-calc-engine
Agent
Analyzes Excel workbooks and creates safe execution plans.
not rated 0 19d ago A 10 tokens
original MIT
engineer
40surajpanwar/advanced-calc-engine
Agent
Executes approved calculations and Excel modifications.
not rated 0 19d ago A 7 tokens
original MIT
surajpanwar/advanced-calc-engine
Agent
Audits the application for security vulnerabilities.
not rated 0 19d ago A 7 tokens
original MIT
analyzer
42Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
not rated 7 4mo ago A 0 tokens
MIT
comparator
43Agent
Compare two outputs WITHOUT knowing which skill produced them.
not rated 7 4mo ago A 0 tokens
MIT
grader
44Agent
Evaluate expectations against an execution transcript and outputs.
not rated 7 4mo ago A 0 tokens
MIT
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: