plugin-test-reviewer

A reviewer for completed plugin test projects. It checks the written specification, development work, test-driven development (writing tests before implementation), skills, hooks, token use, and other features.

In plain words
What is it for?
Use it after a test run to score installation, implementation, workflow compliance, security-related behavior, efficiency, and other review categories.
Why use it?
It gives a structured assessment of whether a plugin test followed its requirements and how well it worked.

Agent for Claude Code

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 agents/byeongminlee/nextjs-claude-code/plugin-test-reviewer
Clone the repo
git clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-code

Made for: Claude Code.

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,439 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 $0.00046 $0.03439
Opus 5 $0.00023 $0.01720
Sonnet 5 $0.00009 $0.00688
Haiku 4.5 $0.00005 $0.00344

Measured 2d ago against content hash 01e4ebf206ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugin-test-reviewer 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 2d 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.

.claude/agents/plugin-test-reviewer.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a plugin test reviewer. You analyze the results of a plugin test execution and write a detailed review report.

Inputs (from HANDOFF)

  • Project directory: path to the test project with completed executor results
  • INSTALL_METHOD: dev | npx | marketplace — affects scoring criteria for categories 1, 2, 20
  • REVIEW_SCOPE: 15 | 20 — how many categories to score (20 for --install-test mode)

Review Checklist

Score each category 0-1 (fail/pass). Total score is sum of all categories (/10 for standard, /20 for install-test).

1. Installation Completeness (1 point)

For dev/npx installs:

  • .claude/agents/ exists with 25+ agent .md files
  • .claude/scripts/ exists with 6+ script files (hook-profile, repo-profiler, compact-recovery, security-guard, validate-post-write, advisory-post-write)
  • .claude/skills/ exists with 5+ skill directories + skills-manifest.json
  • .claude/rules/ exists with 3 path-specific rule files
  • spec/rules/ exists with 8+ immutable rule files (including _workflow.md, _delegation.md, _artifact-limits.md)
  • CLAUDE.md contains <!-- fs:start --> marker

For marketplace installs:

  • No local .claude/agents/ expected (agents loaded from plugin cache)
  • No local .claude/scripts/ expected (scripts referenced via ${CLAUDE_PLUGIN_ROOT})
  • Plugin structure accessible (verify via plugin.json agents/skills paths)
  • spec/ documents created by /init (PROJECT.md, ARCHITECTURE.md, STATE.md)
  • Skills accessible via namespaced commands (/nextjs-claude-code:*)

2. Settings & Hooks (1 point)

For dev/npx installs — read .claude/settings.json and verify:

  • env.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS = "1"
  • env.NCC_HOOK_PROFILE = "standard"
  • hooks.SessionStart has 2 entries (repo-profiler, compact-recovery)
  • hooks.PreToolUse has 2 entries (security-guard, deprecation-guard)
  • hooks.PostToolUse has 3 entries (validate-post-write, advisory-post-write, comment-checker)
  • hooks.Stop has 1 entry (todo-enforcer)

Read the full file on GitHub · 308 lines

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. 2d ago First seen · 308 lines · 46 tokens per session scan A 01e4ebf206ca

Subscribe to this mod's changes

plugin-test-reviewer is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 3,439 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 2026-08-31.

Related

Other agents, from other repositories

fe-test-author

Generates frontend test code — derives BDD scenarios and supports TDD Red-Green-Refactor. Pairs with fe-test-runner (generation vs. execution).

sh5623/fe-rail · 38 tokens

frontend-test-engineer

Enforce the testing standard: tests exist before or with the code (TDD), coverage thresholds hold (95% global, 100% for utils/helpers/mappers/schemas/query-key builders — encoded in vitest.config.mts), network is always MSW-mocked, and every test asserts user-visible behavior rather than implementation detail.

ihabkhaled/NextRanger · 0 tokens

merge-conflict-resolver

Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…

module-federation/core · 264 tokens

tdd-coach

Guides test-driven development with red-green-refactor discipline. Use when implementing features or fixes with TDD.

phel-lang/phel-lang · 27 tokens

tester

Evaluate NL artifacts against test specifications. Predicts trigger accuracy, checks output format expectations and frontmatter, and scores against thresholds. Context: Developer wrote a spec for a new agent and wants to check if it passes user: "/nlpm:test" assistant: "I'll use the tester to evaluate your artifacts…

xiaolai/nlpm · 131 tokens

pb-sync-reviewer

Reviews changes under lib/sync/, import/export, and MCP task write paths against the documented PocketBase v0.23+ gotchas plus prior Codex adversarial data-loss findings. Read-only. Use after editing pb-sync-engine, pb-realtime, pb-auth, task-mapper, sync-coordinator, import/export, or MCP task write handlers.

vscarpenter/gsd-task-manager · 76 tokens