edd

edd is a skill for Claude Code, Codex from truera/trulens. It costs 63 tokens per session (1,013 once invoked), scanned A, original, MIT.

An evaluation-driven development workflow for a retrieval-augmented generation app, which answers questions using retrieved source documents. It uses TruLens to record traces and judge relevance, grounding, and answer quality.

In plain words
What is it for?
Use it to run retrieval experiments, inspect evaluation feedback, and accept or reject changes to the app's retrieval and generation setup.
Why use it?
It provides an ordered way to run experiments and decide whether a prompt or configuration change should be kept. It also prevents expected answers from being invented instead of taken from the source PDFs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to run retrieval experiments, inspect evaluation feedback, and accept or reject changes to the app's retrieval and generation setup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/truera/trulens/edd
About the project

TruLens is an open-source system for tracing and evaluating LLM applications and AI agents. It records each step's inputs, outputs, latency, tokens, and cost, then uses evaluations to find failures and compare application versions.

truera/trulens · 3,571 stars · on GitHub · trulens.org

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add truera/trulens --skill edd
Clone the repo
git clone --depth 1 https://github.com/truera/trulens

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for edd

README.md
[![agentmods](https://agentmods.dev/badge/skills/truera/trulens/edd/github.svg)](https://agentmods.dev/skills/truera/trulens/edd)
Your own site
<a href="https://agentmods.dev/skills/truera/trulens/edd"><img src="https://agentmods.dev/badge/skills/truera/trulens/edd/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for edd

Your own site · 80×15
<a href="https://agentmods.dev/skills/truera/trulens/edd"><img src="https://agentmods.dev/badge/skills/truera/trulens/edd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,013 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.01013
Opus 5.5 $0.00025 $0.00405
Sonnet 5 $0.00013 $0.00203
Haiku 4.5 $0.00006 $0.00101

Measured today against content hash a05d2d0c9e67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-24, from the pricing page.

Security

Grade A, and why

edd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

examples/experimental/EDD/.agents/skills/edd/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EDD loop for rag-loop with TruLens (aircraft systems)

Orchestration for this repo's eval loop: which command to run, in what order, and what's automated vs. what needs judgment. For TruLens evaluation setup, instrumentation, or feedback functions, reference TruLens core patterns (Feedback, Selector, SpanAttributes).

Stack: LangGraph orchestrates retrieve → generate; retrieval embeddings are OpenAI (text-embedding-3-small, requires OPENAI_API_KEY); generation uses OpenAI (gpt-5.6-luna); TruLens feedback judges use the RAG Triad with OpenAI (gpt-4.1-nano); vector database is Qdrant (QDRANT_URL/QDRANT_API_KEY). Traces and evaluations are recorded via TruLens OpenTelemetry instrumentation and saved in TruLens database.

Two fundamental rules:

  1. Never invent an expected_output. Every golden's expected answer must be lifted from the actual PDF text, not written from general knowledge of aircraft systems.
  2. Grade outcomes, not paths. A judge scores whether the final answer is relevant, grounded in the retrieved context, and directly answers the question.

Preconditions

Everything except reading/editing files needs .env populated:

  • OPENAI_API_KEY
  • QDRANT_URL
  • QDRANT_API_KEY

rag-loop run also requires git tracking to commit accepted changes and revert rejected ones.

What's automated vs. what's your job

rag-loop run <name> (src/rag_loop/loop.py: run_iteration) automates the mechanical steps:

  • Runs the experiment through the RAG pipeline
  • Evaluates with TruLens feedback functions (answer_relevance, groundedness, context_relevance)
  • Computes clean_negative_recall for unanswerable held-out items
  • Persists scores and COT reasons to evals/results/<name>.json
  • Compares against acceptance.compare_against on acceptance.required_metrics
  • Writes the decision back to evals/experiments.json
  • Commits src/ (keep) or reverts via git (reject)

Your job as an agent: read the failures, form a hypothesis, and write the next single-variable change. The iterative cycle:

Read the full file on GitHub · 106 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 106 lines · 63 tokens per session scan A a05d2d0c9e67

Subscribe to this mod's changes

edd is a skill published in the GitHub repository truera/trulens (3,571 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 1,013 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-24.

Related

Other skills, from other repositories

evaluators

Author or refine a Phoenix evaluator — code or LLM-as-a-judge — that scores a run's output. Trigger when the user wants to create a new evaluator, improve an existing one's logic or rubric, choose labels, or decide what to measure on a dataset or experiment. Do NOT trigger on: (1) manual prompt drafting (use…

Arize-ai/phoenix · 114 tokens

playground

Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset. Load before any playground ui. operation call, including single-shot prompt rewrites.

Arize-ai/phoenix · 42 tokens

datasets

Understand what a Phoenix dataset is and reason well about its examples, outputs, splits, and how it feeds evaluators and experiments. Load this whenever a dataset is in view or the user asks what a dataset is, how splits work, what an output "means", or how datasets relate to experiments and evals. This skill governs…

Arize-ai/phoenix · 78 tokens

experiments

Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving. Trigger when the user wants to iterate over a dataset with experiments, compare experiment runs, read experiment quality/latency/cost, or decide whether a change actually helped. Running a prompt over a dataset…

Arize-ai/phoenix · 165 tokens

phoenix-client-development

Development guide for the @arizeai/phoenix-client TypeScript SDK — run and resume experiments, manage OpenTelemetry tracer providers with stack-based attach/detach, and write vitest unit and integration tests. Use when adding features to phoenix-client, debugging experiment lifecycle or provider cleanup, modifying…

Arize-ai/phoenix · 85 tokens

b02-skills-main--datascience

🤖 Data Science Engineering Skills — TDD and planning skills for ML pipelines, data APIs and analytical tooling. Derived from skills-main (mattpocock/skills). Data pipelines, model training, evaluation, MLOps.

ChamberTeller/b02-skills-main-datascience · 56 tokens