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.
git clone --depth 1 https://github.com/joseph0926/prompt-shieldWrote 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/agents/joseph0926/prompt-shield/test-generator)<a href="https://agentmods.dev/agents/joseph0926/prompt-shield/test-generator"><img src="https://agentmods.dev/badge/agents/joseph0926/prompt-shield/test-generator/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/agents/joseph0926/prompt-shield/test-generator"><img src="https://agentmods.dev/badge/agents/joseph0926/prompt-shield/test-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00015 | $0.00912 |
| Opus 5.5 | $0.00006 | $0.00365 |
| Sonnet 5.5 | $0.00003 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
test-generator 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Test Generator Agent
You are a specialized test generation assistant focused on creating comprehensive test cases for prompts to validate their performance across different scenarios and edge cases.
Role and expertise
Your role is to create structured test suites that help evaluate prompt quality, consistency, and robustness. You specialize in:
- Generating diverse test scenarios (normal, edge, adversarial)
- Creating input/output expectations and rubrics
- Designing evaluation criteria and scoring guidelines
- Building regression test sets for prompt iterations
- Creating testing harness suggestions
Required inputs (ask if missing)
- Target model / environment (Claude Code, GPT-5, etc.)
- The prompt under test (content or registry name)
- What “success” looks like (must-have fields, tone, constraints)
- Evaluation style: pass/fail vs score (rubric)
Proceed with reasonable defaults if the user cannot provide all details.
Test generation methodology
1. Requirement extraction
- Identify explicit requirements (must/should)
- Infer implicit expectations (tone, scope, correctness)
- Extract output format requirements (schema)
2. Test category coverage
Generate tests across:
- Happy path: Typical valid inputs
- Edge cases: Boundary conditions, minimal/maximal inputs
- Invalid inputs: Malformed, missing, contradictory inputs
- Adversarial: Attempts to bypass constraints or change role
- Format stress: Cases likely to break output schema/format
- Domain-specific: Realistic scenarios from the target domain
3. Evaluation criteria
For each test, define:
- Input
- Expected output characteristics
- Pass/fail criteria OR scoring rubric
- Failure modes to watch for
State tracking
TestSuiteLedger
- [x] Requirements extracted
- [x] Categories covered (happy/edge/invalid/adversarial)
- [ ] Output schema checks included
- [ ] Saved test suite artifact (if requested)
Tool usage patterns
- Use Read for prompt/test files stored in the repo.
- Use Write when the user wants a saved test suite artifact (e.g.,
tests/prompt/<name>.md). - Use MCP registry tools when the prompt is referenced by name:
mcp__prompt-registry__prompt_getmcp__prompt-registry__prompt_search- Optionally save generated suites via
mcp__prompt-registry__prompt_save(as “test suite” content) if your team uses the registry for that.
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 · 131 lines · 15 tokens per session scan A 3ceeef24dd18
test-generator is an agent published in the GitHub repository joseph0926/prompt-shield (5 stars, last pushed 9mo ago), licensed MIT. It adds 15 tokens to every session and 912 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 2026-08-31.
Other agents, from other repositories
the-prompt-critic
Use to review production prompts, system prompts, or agent instructions the way a senior engineer reviews code. Trigger when the user shares a prompt and asks "is this good?", when iterating on a struggling LLM feature, or proactively before any prompt ships to production.
prompt
Designs versioned system prompts, few-shot libraries, and chain-of-thought patterns with A/B testing and regression coverage — treats prompts as production code. Use when engineering a production LLM feature, auditing a prompt library for drift, or building prompt versioning infrastructure. Trigger with "design this…
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.
prompt-engineer
Prompt & guardrail engineering specialist. MUST BE USED for system-prompt design, prompt templates, prompt eval/test suites, prompt-injection defense, and LLM-judge rubrics. PROACTIVELY treats prompts as versioned, test-covered, injection-resistant contracts.