neurodock: Agent for Claude Code

.claude/agents/evals-expert.md

evals-expert is an agent for Claude Code from tlennon-ie/neurodock. It costs 106 tokens per session (3,042 once invoked), scanned A, original, AGPL-3.0.

An agent responsible for the evaluation packages of a software project. These packages contain versioned test examples and an offline test system for checking prompt-related changes in continuous integration, or CI.

In plain words
What is it for?
Use it for work in packages/evals/, including evaluation datasets, test categories, schema checks, the offline runner, scoring, anonymisation, and deduplication.
Why use it?
It provides a controlled way to check whether changes to translation and safety prompts still behave correctly, including checking the test format, scores, duplicates, and anonymised data.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is tlennon-ie/neurodock's own configuration. It tells Claude Code how to work on neurodock itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything neurodock configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tlennon-ie/neurodock. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tlennon-ie/neurodock/main/.claude/agents/evals-expert.md
Clone the repo
git clone --depth 1 https://github.com/tlennon-ie/neurodock

Made for: Claude Code.

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 evals-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/tlennon-ie/neurodock/evals-expert/github.svg)](https://agentmods.dev/agents/tlennon-ie/neurodock/evals-expert)
Your own site
<a href="https://agentmods.dev/agents/tlennon-ie/neurodock/evals-expert"><img src="https://agentmods.dev/badge/agents/tlennon-ie/neurodock/evals-expert/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 evals-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/tlennon-ie/neurodock/evals-expert"><img src="https://agentmods.dev/badge/agents/tlennon-ie/neurodock/evals-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,042 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 unknown 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 $0.00106 $0.03042
Opus 5 $0.00053 $0.01521
Sonnet 5 $0.00021 $0.00608
Haiku 4.5 $0.00011 $0.00304

Measured 9d ago against content hash 779556275e5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

evals-expert 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 9d ago.

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.

.claude/agents/evals-expert.md · 181 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 9d ago First seen · 181 lines · 106 tokens per session scan A 779556275e5e

Subscribe to this mod's changes

evals-expert is an agent published in the GitHub repository tlennon-ie/neurodock (11 stars, last pushed 9d ago), licensed AGPL-3.0. It adds 106 tokens to every session and 3,042 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 2026-08-30.

Related

Other agents, from other repositories

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens

skill-eval-grader

Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.

QBall-Inc/the-bulwark · 53 tokens

mb-qa

QA / testing specialist for memory-bank /mb work stages. Test design, coverage strategy, edge-case enumeration, flake elimination, contract tests. Falls back to mb-developer when stage is generic.

fockus/skill-memory-bank · 44 tokens

test-expert-csk

Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".

byerlikaya/claude-starter-kit · 41 tokens

gsd-eval-planner

Designs a structured evaluation strategy for an AI phase. Identifies critical failure modes, selects eval dimensions with rubrics, recommends tooling, and specifies the reference dataset. Writes the Evaluation Strategy, Guardrails, and Production Monitoring sections of AI-SPEC.md. Spawned by /gsd:ai-integration-phase…

gsd-build/get-shit-done · 72 tokens

_qa

Senior QA Engineer that creates test plans and executes comprehensive testing including auth flows and edge cases. Trigger on testing, QA, test plan, regression, bug report, or auth flow testing.

navox-labs/agents · 40 tokens