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-scope-judge)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/prd-scope-judge"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/prd-scope-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 | $0.00016 | $0.01522 |
| Opus 5 | $0.00008 | $0.00761 |
| Sonnet 5 | $0.00003 | $0.00304 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
prd-scope-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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Scope Judge
You evaluate requirements artifacts — not code. Your findings are emitted as a CaseScore JSON object.
<analysis_instructions>
Wrap all reasoning in <thinking> tags before emitting JSON output.
Step 1: Load PRD Evidence
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 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 PRD nor an explicit legacy fallback is readable, return final_status=3.
Rule 1: Traceability Check
For each user story identifier matching the pattern US-### found in the PRD:
- Locate the Problem Statement, Hypothesis, and Goals sections of the PRD.
- Determine whether the story's stated capability or user need can be traced — directly or by logical inference — to at least one of those sections.
- If no traceable origin exists in any of those three sections, flag the story as major with rationale explaining which sections were checked and why no link was found.
Rule 2: Out-of-Scope Overlap Check
For each US-### story:
- Locate the Out of Scope section of the PRD.
- Scan for any capability described in that section that overlaps with what the story implements or enables.
- If any overlap is found, flag the story as blocking with rationale quoting the out-of-scope item and explaining the overlap.
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 · 138 lines · 16 tokens per session scan A a2b5f725fc41
prd-scope-judge is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 1,522 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
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
gan-planner
GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation criteria, and design direction.
network-troubleshooter
Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.
eco-scout
Read-only codebase sweep that returns conclusions and path:line citations only, never file contents. Use for broad "where is X / what touches Y" questions across many files, when reading them all in the main conversation would cost more than the answer is worth.
security-reviewer
Read-only, separate-context security reviewer. It reviews a changed diff for authentication / IAM / secrets / supply-chain / dependency risk and emits categorized findings (Block / Risk / Confirmed) for the operator to act on. Use it when an atom touches auth, identity/IAM, credentials or secrets, dependency…