sample-agent
01Agent
A sample agent for testing purposes.
Agent
A sample agent for testing purposes.
Agent
Validation agent for testing Copilot CLI agent delegation and structured output.
Agent
Worker agent for testing parallel sub-agent execution with file-backed JSON handoff.
Agent
Maps system architecture patterns, layers, and integrations for architecture.md from pre-filtered files.
Agent
Extracts domain concepts and terminology for conceptmap.md from pre-filtered files.
Agent
Extracts project capabilities and feature inventory for features.md from pre-filtered anchor-class files.
Agent
You are IndexBuilder-GPT, a specialized agent that creates project overview data for the knowledge base index.md file. You receive a pre-filtered list of high-priority files and extract key project information.
Agent
Maps cross-surface interaction semantics for interaction-model.md from pre-filtered files.
Agent
Analyzes modules, components, and dependencies for modules.md from pre-filtered files.
Agent
Extracts implementation patterns and idioms for patterns.md from pre-filtered source files.
Agent
Scans repository files, ranks by importance (0-5), and categorizes them by KB section for parallel analysis.
Agent
Validates and repairs mermaid diagrams in markdown files. Scans for mermaid blocks, validates each diagram, attempts automatic repair (up to 3 iterations), and inserts placeholders for unfixable diagrams.
Agent
Generates a digestible 3-tier/9-section birds-eye-view document from KB + codebase, with per-claim provenance in hidden HTML comments.
Agent
Executes the six-stage prompt-writer pipeline and produces two mandatory output artifacts (ready-to-run prompt, confidence report).
Agent
Deep exploration of codebases or web resources, returning structured JSON findings with evidence.
Agent
Generates structured research reports with validated Mermaid diagrams from synthesis data.
Agent
Dual-mode doc worker for scan/process batches. Returns JSON only.
Agent
Performs evidence-bounded, standards-mapped security posture assessment for a project, sub-directory, module, concept, or feature topic.
Agent
Participates in a Socratic Duel run using pre-resolved launcher context and participant-owned artifact writes.
Agent
Analyzes systems holistically to provide strategic recommendations balancing cost, quality, performance, complexity, and business objectives with quantified trade-offs.
Agent
Discovers candidate tech debt signals (bloat, dead code, over-abstraction) from target codebase with configurable lens.
Agent
Audits PRD documents against implementation status and executes disposition actions.
Agent
One-shot non-interactive PRD finalizer that preserves authored requirements, derives completion from required sections, and reports remaining gaps as raw JSON.
Agent
One-shot non-interactive bootstrap worker for bounded PLAN, REVISE, or APPLY actions.