Execution layer for skill-dispatcher — runs multi-phase agent chains end-to-end with per-step telemetry and chain_id correlation

Audit and reduce YAML frontmatter bloat in AgentSkill SKILL.md files. Automates deduplication, flattening, and noise removal.

RL-style eval measuring intent/action divergence in frontier agents: model acknowledges a correction, then acts on the stale value anyway. 3 scenarios, 655 trials on claude-haiku-4-5, Sonnet 4.6, GPT-5.4, and Gemini 3.1 Pro Preview.

Produces auditable token-usage and cost reports from runtime evidence, normalized usage bundles, and repository-level report sets.

Audits frontend implementations for design-system drift across CSS, Tailwind, JSX, TSX, Vue, and Angular code.

Manages durable cross-agent shared memory for stable conventions, reusable policies, and organization-wide operating rules.

Audits APIs against OpenAPI, AsyncAPI, JSON Schema, protobuf, or PRD contracts to catch drift before release.

High-performance routing engine that selects the best agent skill for a task and emits structured handoff decisions.

Scores and improves prompts for clarity, consistency, signal density, structure, and runtime fit.

MCP server for AI agent research — captures LLM reasoning, model identity, and feedback via schema injection