What is anthropic-prompt-eval?

A reference and implementation guide for designing and evaluating prompts for Claude through its API. It covers prompt structures, examples, testing methods, security issues, and common AI tasks.

Use it to design Claude prompts, build evaluations and grading, and implement tasks such as ticket routing or classification.

It helps developers create prompts and tests while addressing problems such as jailbreaks, prompt leaks, made-up answers, and unreliable classification.

anthropic-prompt-eval — Skill for Claude Code by Fandhe-AI

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 Fandhe-AI/agent-reference-skills --skill anthropic-prompt-eval

Clone the repo

git clone --depth 1 https://github.com/Fandhe-AI/agent-reference-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fandhe-ai/agent-reference-skills/anthropic-prompt-eval/github.svg)](https://agentmods.dev/skills/fandhe-ai/agent-reference-skills/anthropic-prompt-eval)

Your own site

<a href="https://agentmods.dev/skills/fandhe-ai/agent-reference-skills/anthropic-prompt-eval"><img src="https://agentmods.dev/badge/skills/fandhe-ai/agent-reference-skills/anthropic-prompt-eval/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fandhe-ai/agent-reference-skills/anthropic-prompt-eval"><img src="https://agentmods.dev/badge/skills/fandhe-ai/agent-reference-skills/anthropic-prompt-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,027 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.

Model	Per session	Once invoked
Fable 5.1	$0.00105	$0.01027
Opus 5	$0.00053	$0.00513
Sonnet 5	$0.00021	$0.00205
Haiku 4.5	$0.00011	$0.00103

Measured 12d ago against content hash f38fc1554c90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

anthropic-prompt-eval 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 12d 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.

skills/anthropic-prompt-eval/SKILL.md · 80 lines

The source is not reproduced here

No licence file

Read it on GitHub

Files

What ships with it

30 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.

12d ago First seen · 80 lines · 105 tokens per session scan A f38fc1554c90

Subscribe to this mod's changes

anthropic-prompt-eval is a skill published in the GitHub repository Fandhe-AI/agent-reference-skills (3 stars, last pushed today), with no licence file. It adds 105 tokens to every session and 1,027 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 2026-08-31.

Data and AI Prompting Testing

darwinian-evolver

Evolve prompts/regex/SQL/code with Imbue's evolution loop.

NousResearch/hermes-agent · 22 tokens

promptfoo-evaluation

Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM…

daymade/claude-code-skills · 86 tokens

prompt-regression

Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change help," or prompt…

agentscope-ai/OpenJudge · 86 tokens

anthropic-prompt-eval