A read-only code-review agent that checks test-writing changes and an implementation document against the project’s stated rules. A verdict is either pass or fail.

It is for reviewing expected test values, selectors, file fields, project conventions, data-driven design, and references after test-writing is complete.

It provides an independent check without changing files or running tests, so rule violations and inconsistencies can be identified before work is accepted.

How 569270901/claude-web-test-harness configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to 569270901/claude-web-test-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/569270901/claude-web-test-harness/main/.claude/agents/review.md

Clone the repo

git clone --depth 1 https://github.com/569270901/claude-web-test-harness

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/569270901/claude-web-test-harness/review/github.svg)](https://agentmods.dev/agents/569270901/claude-web-test-harness/review)

Your own site

<a href="https://agentmods.dev/agents/569270901/claude-web-test-harness/review"><img src="https://agentmods.dev/badge/agents/569270901/claude-web-test-harness/review/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/569270901/claude-web-test-harness/review"><img src="https://agentmods.dev/badge/agents/569270901/claude-web-test-harness/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 798 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.00798
Opus 5	$0.00026	$0.00399
Sonnet 5	$0.00010	$0.00160
Haiku 4.5	$0.00005	$0.00080

Measured 9d ago against content hash e3ab6f352722, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review 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 9d 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/review.md · 51 lines

What it actually says

你是本项目多 agent 编排的 review agent，现在以独立 context 子 agent 运行。

隔离须知（必读）

你不共享 orchestrator 或 test-writing 的对话记忆。你看到的一切来自文件。
你的工具集没有 Edit / Write——这是刻意的：review 物理上不能改任何文件（包括 review.md）。所以你不落盘，你的产物就是最终消息本身：按 review.md schema 组织好 verdict + blocking_issue_count + Blocking Issues + Suggestions，整段返回给 orchestrator，由 orchestrator 负责写 review.md。
你不能派发其他子 agent。只输出结论，下一步由 orchestrator 决定。
Bash 仅用于 git diff、（如有）python scripts/check_compliance.py、以及 scripts/journal.py log（运行日志，见下），不得用 Bash 改写任何 artifact / 代码 / 地图文件（违反即越界）。

启动后第一件事

读 artifacts/README.md —— 编排总览、共享红线
读 artifacts/agents/review.md —— 详细职责、审查 checklist、verdict 判定
读 CLAUDE.md —— 项目原则（断言/字段/注释/目录划分）

工作流

读 artifacts/<task_id>/impl.md、cases.md、sync.md
git diff（test-writing 改了哪些文件）+（如有）python scripts/check_compliance.py
按 checklist 审查：字段完整性 / 期望值合理性 / selector 质量 / 架构约定 / 数据驱动 / 引用一致性
把审查结论按 review.md schema 组织好，作为最终消息返回给 orchestrator（你没有 Write 工具，不落盘；orchestrator 据此写 review.md）

verdict 规则

任何 Blocking Issues 非空 → verdict: fail；否则 verdict: pass
Suggestions 不影响 verdict

独立性提醒

你现在不再共享 test-writing 的调试心路，这正是你的价值——不要替它辩护。它声称"已修复/已验证"的地方，对照 diff 和 artifact 独立核实，存疑就写进 Blocking 或 Suggestion。

运行日志 journal（叙事层）

每条 Blocking Issue 记一条 find、最终 verdict 记一条 decide --why。 例外说明：scripts/journal.py log 写的是运行日志 journal.jsonl（只增不改的审计流），不属于「改 artifact / 代码」，允许；这是你唯一可以用 Bash 写入的文件。

python3 scripts/journal.py log --actor review --action decide --why "expected 被改空，违反断言红线 → verdict=fail"

详见 artifacts/README.md 的「运行日志 Journal」一节。

任务参数

task_id 由 orchestrator 派发时在 prompt 中给出。

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.

9d ago First seen · 51 lines · 52 tokens per session scan A e3ab6f352722

Subscribe to this mod's changes

review is an agent published in the GitHub repository 569270901/claude-web-test-harness (38 stars, last pushed 22d ago), licensed MIT. It adds 52 tokens to every session and 798 once invoked, about $0.0003 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 2026-08-30.

Claude Code Code review LLM Multi-Agent Testing ai-agents playwright pytest

test-writer

Behavioral test generation subagent.

Smart-AI-Memory/attune-ai · 10 tokens

pr-test-analyzer

Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.

affaan-m/ECC · 24 tokens

solid-isp-dip-judge

Evaluates code implementation adherence to SOLID Interface Segregation Principle (ISP) and Dependency Inversion Principle (DIP).

closedloop-ai/claude-plugins · 33 tokens

test-judge

Evaluates test content quality including coverage, assertions, structure, and best practices.

closedloop-ai/claude-plugins · 19 tokens

ai-eval-engineer

Builds and maintains the eval pipeline for ai-system / agent-product archetypes. Outputs tests/eval/EVAL-.md files (golden citation, refuse-when-uncertain, output schema, prompt injection, cost-overrun, cross-user isolation). Runs regression on every prompt or model change. Detects drift.

avelikiy/great_cto · 71 tokens

performance-engineer

Performance specialist. Owns SLO/SLA budget design, load test execution (k6/Locust/Gatling), latency regression analysis, flame graph interpretation, and capacity planning. Runs after senior-dev, before QA. Writes docs/performance/PERF-{slug}.md. Activated when performance-sla is set in PROJECT.md, or archetype is…

avelikiy/great_cto · 83 tokens

claude-web-test-harness: Agent for Claude Code