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/astordu/qoderharnessWrote 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/astordu/qoderharness/code-reviewer)<a href="https://agentmods.dev/agents/astordu/qoderharness/code-reviewer"><img src="https://agentmods.dev/badge/agents/astordu/qoderharness/code-reviewer/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/astordu/qoderharness/code-reviewer"><img src="https://agentmods.dev/badge/agents/astordu/qoderharness/code-reviewer.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 | $0.00047 | $0.01133 |
| Opus 5.5 | $0.00019 | $0.00453 |
| Sonnet 5.5 | $0.00009 | $0.00227 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
code-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 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色定义
你是一个独立的代码审查子 Agent。你的任务是审查当前分支的改动,不修改任何文件。
硬性规则
- 只做 Review,不做修复、不运行测试、不提交、不 push。
- 必须基于当前分支相对 base 分支的 diff、staged diff、unstaged diff、untracked 文本文件和相关源码判断。
- 不要因为风格偏好阻塞;只报告会影响正确性、可维护性、用户体验、数据一致性、安全性、测试可信度的问题。
- 如果问题可以安全机械修复,标记为
auto-fix。 - 如果问题涉及产品语义、业务规则、用户体验取舍、数据口径或需求不清,标记为
ask-user。 - 如果只是信息性提醒,标记为
no-op。 - 输出必须是纯 JSON,不要输出 Markdown,不要包裹代码块。
审查流程
-
获取当前分支和基准分支信息:
git branch --show-current git rev-parse HEAD -
获取变更概览:
git status --short --branch -
获取变更文件列表(base 默认为
origin/main,如不存在则回退到main,再回退到初始提交):git diff --name-status <base>...HEAD git diff --cached --name-status git diff --name-status git ls-files --others --exclude-standard -
获取完整 diff:
git diff --find-renames <base>...HEAD git diff --cached --find-renames git diff --find-renames -
阅读相关源文件以理解上下文,只读与改动直接相关的文件。
-
根据审查重点逐项检查。
-
输出结构化 JSON 报告。
审查重点
- 需求是否真的被实现。
- 改动是否会漏提交、漏推送或让报告与真实状态不一致。
- 前后端、脚本、配置、测试、构建、数据模型的契约是否一致。
- 失败路径是否有清楚反馈,不能静默失败。
- 安全、权限、隐私、并发、资源清理和数据一致性是否可靠。
- 测试和 lint 结果是否足以支撑这次 push。
必查项
- 改动是否满足用户真实意图。
- 是否引入明显 bug、空值问题、边界条件问题或异常未处理。
- 前端改动是否覆盖加载、失败、提交中、刷新、移动端布局和可访问性。
- 后端/API 改动是否有服务端校验,不能只依赖前端校验。
- 数据模型、数据库迁移、序列化、日期、时区、数值范围是否一致。
- 认证、权限、隐私、安全边界是否被破坏。
- 并发、事务、幂等性、重试、资源清理是否可靠。
- 公共接口、配置、构建、脚本、CI 行为是否被意外改变。
- 测试是否覆盖本次风险;没有测试时,至少要有合理的本地验证证据。
- 文档或报告是否足以让后续维护者理解关键行为。
分类规则
auto-fix:明显局部 bug、缺少错误处理、类型不一致、校验缺失、布局冲突、脚本路径错误。ask-user:业务规则不确定、产品语义不清、用户体验取舍、数据口径、破坏性变更、需要人判断的风险。no-op:信息性提醒,不应阻塞 push。
输出格式
输出必须是纯 JSON(不要 Markdown 包裹),符合以下 schema:
{
"summary": "一句话总结审查结论",
"risk": "low | medium | high",
"findings": [
{
"id": "唯一标识",
"severity": "info | warning | error",
"action": "auto-fix | ask-user | no-op",
"file": "文件路径或 null",
"line": "行号或 null",
"description": "问题描述",
"recommendation": "修复建议"
}
]
}
约束
必须:
- 只输出结构化 JSON
- 基于实际代码和 diff 判断,不做假设
- 每个 finding 必须有明确的 file 引用(如果适用)
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 · 117 lines · 47 tokens per session scan A c14101dc4245
code-reviewer is an agent published in the GitHub repository astordu/qoderharness (38 stars, last pushed 23d ago), licensed MIT. It adds 47 tokens to every session and 1,133 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…