effortless

Promptfoo is an AI application security and evaluation platform for testing prompts, RAG systems, agents, models, and guardrails. It can run evaluation tests with LLM-judge scoring against defined criteria and verify citations against source documents; in the described payment-rules assistant, it was used to assess answer quality and investigate apparent regressions against the underlying evidence. Its security workflows simulate context-aware attacks, including prompt injection, jailbreaks, data leaks, business-rule violations, insecure agent tool use, and toxic-content generation, and can run in development and CI/CD workflows. Promptfoo also provides automated red teaming, code scanning, MCP security testing, remediation guidance, and continuous monitoring, with integrations for AI applications, agent frameworks, CI/CD systems, and on-premises or cloud deployments.

fast-jev-compaction is an npm library and Claude Code plugin that compacts tool-call history without rewriting the original text. It pairs each tool call with its result, sends the conversation state and questions about each non-pinned call to Jev, and then keeps the call and result, keeps only the call while truncating the result, or removes both according to Jev's scores. Recent messages and the first message are pinned; state fitting progressively truncates inputs, abridges long text, collapses older messages, and reduces old tool calls to one-line records so requests fit within configured token estimates. User and assistant text is never removed or shortened in the returned transcript, and retained content stays verbatim. The package exposes compaction, decision, batching, state-fitting, and transport-building functions, while the Claude Code hook replaces built-in compaction and falls back to Claude Code's summary when Jev fails or reduction is insufficient. It uses the TypeSafe API by default and requires a TypeSafe API key.

claudish-to-english is a Claude Code plugin that uses a language model to produce a plain-language rewrite of each assistant message while leaving Claude's reasoning and saved transcript unchanged. Its display hook buffers streamed message chunks, rewrites the completed message through Ollama by default or through the Codex CLI, Anthropic API, or an OpenAI-compatible API, and displays the result in append or replace mode. It follows the input or configured output language and supports configurable rewrite styles, prompts, models, and runtime toggles through the /claudish command and environment variables. An optional PostToolUse hook rewrites Markdown files in a configured directory into a sibling .plain.md file or in place. The hooks fail open: provider errors, missing dependencies or keys, timeouts, unavailable models, and capped outputs leave the original message or file unchanged.

DSPy is a framework for defining language-model program contracts—inputs, output schemas, and scoring functions—so prompt and instruction optimization becomes a search problem. In the described workflow, it searches for shorter instructions while preserving the application's interface and evaluation contract, with candidate changes checked through repeated model runs, shadow evaluation, and human review of disagreements.