prompt-testing

prompt-testing is a skill for Claude Code, Codex from fusengine/agents. It costs 33 tokens per session (968 once invoked), scanned A, original, MIT.

A skill for comparing two versions of an AI prompt using defined quality, cost, and reliability measures.

In plain words
What is it for?
Use it to prepare test cases, run an A/B comparison, calculate metrics, assess statistical confidence, and decide whether to keep or change a prompt.
Why use it?
It replaces guesswork with a repeatable test before adopting a new prompt. It also accounts for edge cases and token usage.

Skill for Claude CodeCodex

Part of the fuse-prompt-engineer plugin — 6 skills, 2 commands, 7 agents shipped together

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.

agentmods
npx agentmods add skills/fusengine/agents/prompt-testing
Any agent
npx skills add fusengine/agents --skill prompt-testing
Clone the repo
git clone --depth 1 https://github.com/fusengine/agents

Made for: Claude Code, Codex.

Or install fuse-prompt-engineer, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 7 agents.

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 prompt-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/fusengine/agents/prompt-testing.svg)](https://agentmods.dev/skills/fusengine/agents/prompt-testing)
Your own site
<a href="https://agentmods.dev/skills/fusengine/agents/prompt-testing"><img src="https://agentmods.dev/badge/skills/fusengine/agents/prompt-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 968 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00968
Opus 5 $0.00016 $0.00484
Sonnet 5 $0.00007 $0.00194
Haiku 4.5 $0.00003 $0.00097

Measured yesterday against content hash b5a7158e738b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prompt-testing 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 yesterday.

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.

plugins/prompt-engineer/skills/prompt-testing/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The adoption decision is rule-based: adopt B if its accuracy is at least equal with acceptable token cost, consider B as a trade-off if accuracy improves >10% despite <20% token regression, otherwise keep A or iterate. Requires a minimum of 20 test cases with 15-20% edge cases for statistical significance.

Prompt Testing

Skill for testing, comparing, and measuring prompt performance.

References

  • metrics.md - Load when: defining or scoring Quality/Efficiency/Robustness/UX metrics with thresholds and calculation formulas
  • methodology.md - Load when: running a full A/B test (hypothesis, dataset sizing, statistical significance, common pitfalls)
  • templates.md - Load when: writing a test dataset JSON or an A/B test report

Testing Workflow

1. DEFINE
   └── Test objective
   └── Metrics to measure
   └── Success criteria

2. PREPARE
   └── Variants A and B
   └── Test dataset
   └── Baseline (if existing)

3. EXECUTE
   └── Run on dataset
   └── Collect results
   └── Document observations

4. ANALYZE
   └── Calculate metrics
   └── Compare variants
   └── Identify patterns

5. DECIDE
   └── Recommendation
   └── Statistical confidence
   └── Next iterations

Performance Metrics

Quality

Metric Description Calculation
Accuracy Correct responses Correct / Total
Compliance Format adherence Compliant / Total
Consistency Response stability 1 - Variance
Relevance Meeting the need Average score (1-5)

Read the full file on GitHub · 127 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. yesterday First seen · 127 lines · 33 tokens per session scan A b5a7158e738b

Subscribe to this mod's changes

prompt-testing is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 968 once invoked, about $0.0002 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

ai-workflow-architect

Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…

cbrock84/headcount · 89 tokens

build-dotnet-agent-service

Build a local-first F# or C# Semantic Kernel agent service with explicit tools, model capability checks, evaluation fixtures, and draft-before-write promotion.

gaelic-ghost/socket · 36 tokens

craft-ai

The Craftsman standard for LLM-powered features — prompt-injection surface, key and spend protection, PII reaching model APIs, and reliability/eval discipline. Use whenever work touches an LLM integration: a chatbot or agent, a RAG pipeline, an LLM call from a route or job, tool/function-calling, or reviewing prompts…

gul-labs/craftsman-marketplace · 129 tokens

expert-ai-engineer

AI/ML engineering specialist — LLM integrations, prompt design, RAG pipelines, embeddings, evals, fine-tuning decisions, agent architectures. Use for any task involving model APIs, prompts, vector stores, or ML tradeoffs. Normally invoked by model-router.

mehtab78/skills · 59 tokens

prompt-cookbook

Build a prompt cookbook for one company's actual vertical and roles rather than generic examples. Each recipe names the job it does, who runs it, the prompt itself, what good output looks like, and how to tell when it went wrong. Written for people who have never written a prompt and will not read documentation about…

enalbenerraw/blanewarrene · 69 tokens

prompt-fixer

Clean up and clarify a rough prompt before acting on it — fix typos, expand a terse or single-word ask into a clear instruction, repair broken or unclosed {{template}} placeholders, substitute known variables, and strip filler openers. Use whenever a request looks hasty: obvious misspellings, a vague one-or-two-word…

Soumya7681/prompt-fixer · 0 tokens