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.
npx skills add fusengine/agents --skill prompt-testinggit clone --depth 1 https://github.com/fusengine/agentsWrote 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.
[](https://agentmods.dev/skills/fusengine/agents/prompt-testing)<a href="https://agentmods.dev/skills/fusengine/agents/prompt-testing"><img src="https://agentmods.dev/badge/skills/fusengine/agents/prompt-testing/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.
<a href="https://agentmods.dev/skills/fusengine/agents/prompt-testing"><img src="https://agentmods.dev/badge/skills/fusengine/agents/prompt-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00968 |
| Opus 5.5 | $0.00013 | $0.00387 |
| Sonnet 5.5 | $0.00007 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
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 1mo 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.
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) |
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.
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.
- 1mo ago First seen · 127 lines · 33 tokens per session scan A b5a7158e738b
prompt-testing is a skill published in the GitHub repository fusengine/agents (33 stars, last pushed 7d ago), licensed MIT. It adds 33 tokens to every session and 968 once invoked, about $0.0001 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 2026-09-03.
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…
16-ai-llm-security
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments.
eval-llm-judge
Write LLM-as-judge evaluator prompts for AI products. Use this skill whenever you need to evaluate semantic properties of AI outputs that cannot be checked programmatically — output quality, tone, factual accuracy, edge case handling, reference alignment. Also use when auditing existing judge prompts for bias…
performance:hill-climb
Use when asked to make software faster or leaner (runtime, startup, throughput, memory, bundle size) through repeated measured changes. For prompts or skills scored by an eval suite, use prompting:hill-climb.
verify-eval-review
A conditional review workflow for checking whether an AI feature has enough evaluation coverage. It compares the implementation with the planned evaluation areas and records each one as covered, partly covered, or missing in EVAL-REVIEW.md.
evaluating-as-user
Evaluates software quality from an end user's perspective. Use when emulating a real user to assess a running web app, CLI tool, or API.