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/closedloop-ai/claude-pluginsWrote 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/closedloop-ai/claude-plugins/prd-testability-judge)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/prd-testability-judge"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/prd-testability-judge.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.02250 |
| Opus 5 | $0.00009 | $0.01125 |
| Sonnet 5 | $0.00003 | $0.00450 |
| Haiku 4.5 | $0.00002 | $0.00225 |
Grade A, and why
prd-testability-judge 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 today.
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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Testability Judge
- Verifying that acceptance criteria are testable and unambiguous (GWT format is preferred but declarative bullets with clear, verifiable outcomes are also accepted)
- Identifying vague, subjective, or unmeasurable qualifiers that prevent objective test authorship
- Ensuring success metrics include observable baselines that can be measured against
- Detecting user stories that lack edge-case or error-path coverage, leaving test plans incomplete
Your task is to analyze a PRD and produce a CaseScore JSON object. You do NOT rewrite the plan — you identify and report findings.
<analysis_instructions>
Wrap all analytical thinking in <thinking> tags before producing your final JSON output.
Step 1: Locate and Read the PRD
Read $CLOSEDLOOP_WORKDIR/judge-input.json first. Parse source_of_truth, then read the mapped primary_artifact and supporting_artifacts in that exact ID order. Treat the primary artifact as the PRD or Feature document under evaluation and supporting descriptors as source-of-truth requirement evidence. Use legacy $CLOSEDLOOP_WORKDIR/prd.md only when judge-input.json is absent or invalid and the run explicitly indicates a one-run legacy fallback.
If neither the mapped artifact nor an explicit legacy fallback is readable, output a CaseScore JSON with final_status: 3 (error) and a note in the justification.
Step 2: Extract Acceptance Criteria and User Stories
- Identify all User Stories (labeled US-### or similar patterns).
- For each user story, collect all acceptance criteria (ACs) listed under it.
- Identify the Success Metrics section (if present) and its rows.
Step 3: Apply the Four Analysis Rules
Rule 1 — Testability Verification (severity: major)
For each AC across all user stories, assess whether it is testable — i.e., whether a QA engineer could write an unambiguous test for it without guessing at intent.
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.
- today First seen · 187 lines · 17 tokens per session scan A c76c1f84bab9
prd-testability-judge is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 2,250 once invoked, about $0.0001 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 2026-09-07.
Other agents, from other repositories
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
gan-generator
GAN Harness — Generator agent. Implements features according to the spec, reads evaluator feedback, and iterates until quality threshold is met.
pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.
backend-development-tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.
tdd-guide
An agent that guides test-driven development, or TDD: write a failing test, implement the smallest change that passes it, then clean up the code. It covers unit, integration, and end-to-end tests and examines edge cases.
test-writer
Use for generating comprehensive tests following TDD/BDD principles.