token-economics

Provenance-bound durable memory with immutable records, append-only review state, active-only recall, and offline semantic recall via a first-party rag provider.

1 skill · 4 commands · 1 MCP server · hooks

Portable, bounded, verified task-state handoffs with manual write/resume commands, a read-only compiler, and deterministic validation.

1 skill · 2 commands · 1 agent

Read-only claim verification and prospective change-impact analysis with per-claim verdicts, blast-radius mapping, and file:line evidence.

2 skills · 1 command · 1 agent

Exhaustive review of a corpus too large to read at once: hashed unit inventory, bounded resumable shards, and a coverage ledger that separates a real gap from an undecidable one.

1 skill · 1 command · 1 agent

Multi-lens evaluative review: independent adversarial, architect, consumer, and operator charters return typed findings that merge on agreement and preserve disagreement as an explicit tradeoff.

1 skill · 1 command · 1 agent

Plan-big / execute-small orchestration: a strong model plans and delegates token-heavy work to cheaper subagents.

1 skill · 1 command · 1 agent

Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.

Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations

24 skills · 1 command · 1 agent · hooks

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.

44 skills · 1 MCP server

Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).

1 skill · hooks