eval-diagnose

eval-diagnose is a skill for Claude Code, Codex from malloydata/publisher. It costs 93 tokens per session (3,079 once invoked), scanned A, original, MIT.

A diagnostic skill that explains why a scored AI answer failed and identifies who owns the fix. It checks possible causes in order, from the dataset and agent request to retrieval, answer construction, and model guidance.

In plain words
What is it for?
Use it after scoring to investigate failed answers, classify the responsible component, and record issues for later improvement.
Why use it?
It prevents teams from changing the model when the real problem is a bad question, missing information, or a retrieval mistake. Related failures can be grouped under one root cause.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after scoring to investigate failed answers, classify the responsible component, and record issues for later improvement.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/malloydata/publisher/eval-diagnose
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 malloydata/publisher --skill eval-diagnose
Clone the repo
git clone --depth 1 https://github.com/malloydata/publisher

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 eval-diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/malloydata/publisher/eval-diagnose.svg)](https://agentmods.dev/skills/malloydata/publisher/eval-diagnose)
Your own site
<a href="https://agentmods.dev/skills/malloydata/publisher/eval-diagnose"><img src="https://agentmods.dev/badge/skills/malloydata/publisher/eval-diagnose.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,079 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00093 $0.03079
Opus 5 $0.00046 $0.01540
Sonnet 5 $0.00019 $0.00616
Haiku 4.5 $0.00009 $0.00308

Measured 4d ago against content hash fb39b1400e2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

eval-diagnose 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/cluster_failures.py, scripts/diagnose.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/eval-diagnose/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose One Answer

Consumes a score event from skill:eval-answer and answers: why did this fail, and who owns the fix?

Scope boundary: write the diagnosis before any edit exists. This skill never edits a model and never proposes a patch beyond naming the gap. Diagnosis that is allowed to edit becomes justification for an edit somebody already wanted.

Do not diagnose a contaminated attempt or an environment failure. Those are harness or ops, not model work.

Components, in order

Walk in this order and stop at the first with positive evidence. A later label requires ruling out the earlier ones. Write component with these strings, never "C1" / "C2" / "C3":

component Question
dataset Bad question, bad or missing golden, or environment drift?
agent-call Did the agent ask for the needed concepts, with the right type and scope?
get_context/model Is the needed entity absent, undocumented, weakly labeled, duplicated, or missing guidance?
get_context/retrieval Was an on-target request against a well-described entity ranked or grouped wrong?
construction Did sufficient context arrive, and the agent still built the wrong query?
model-definition Is a measure, join, filter convention, or source semantically wrong?

owner is separate: model, retrieval, agent-skill, or dataset. There is no environment owner: an environment failure stops the run before diagnosis (see the boundary above), so no issue can carry it.

construction requires proving the needed entities and governing guidance were in the returned context. A server trace proves what Publisher returned, not what the host kept after compaction. If the rendered tool response is gone, mark sufficiency unknown and do not assign construction.

Always report construction eligibility as eligible / total. That is a diagnostic conditional, not a causal comparison.

Step 1: Extract facts from traces, not from memory

For each get_context call, load the stored retrieval trace by the traceId on the tool_call event. Write down, before you interpret anything:

Read the full file on GitHub · 248 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 248 lines · 93 tokens per session scan A fb39b1400e2c

Subscribe to this mod's changes

eval-diagnose is a skill published in the GitHub repository malloydata/publisher (100 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 3,079 once invoked, about $0.0005 per session on Opus 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 2026-09-03.

Related

Other skills, from other repositories

dbt-expert

Expert-level dbt (data build tool), models, tests, documentation, incremental models, macros, and Jinja templating. Use when the user mentions analytics engineering, SQL, data transformation, Jinja, or testing, or when the task involves Project Structure and Configuration, Sources and Staging Models, Intermediate and…

personamanagmentlayer/pcl · 76 tokens

reimagine-it-audit

Design Health — runs 19 deterministic quality checks on HTML output. Use when the user says /reimagine-it audit, "audit this page", "check design quality", or wants to verify craft-floor compliance before shipping. Catches blank plates, missing focus rings, non-compositor motion, off-palette accents, dead motion…

Kayforkind/reimagine-it · 108 tokens

reimagine-it-extract

Emit the content signals reimagine-it reads from an HTML file — title, anchors, proper nouns, dates, numbers, emails, links, source hex colors, and the derived palette — as JSON without generating a redesign. Use when the user says /reimagine-it extract, "what does the engine see in this page", "extract the palette"…

Kayforkind/reimagine-it · 133 tokens

reusable-visualization

Build ONE reusable chart visualization component that receives its data and its settings from the host application instead of fetching them, and declares the fields and config options the host exposes to viewers. Use this whenever a single chart component is reused across many different queries rather than built for…

lightdash/lightdash · 102 tokens

lightdash-agent-slack-messaging

Use this skill when writing, designing, or generating Slack messages for Lightdash's in-app analytics agent. Triggers when someone asks to create agent update messages, Slack digests, agent notifications, weekly summaries, daily summaries, or any Slack copy for the Lightdash project agent. Also use when asked to vary…

lightdash/lightdash · 114 tokens

developing-in-lightdash

Use when reading, creating, and editing Lightdash dashboards and charts as JSON, including dashboard layout and chart-type-specific configuration.

lightdash/lightdash · 31 tokens