Borrowing it
Nothing to install: this file belongs to VoidTechnology/voidtech-claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/VoidTechnology/voidtech-claude-plugins/main/.claude/agents/loop-security-reviewer.mdgit clone --depth 1 https://github.com/VoidTechnology/voidtech-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/voidtechnology/voidtech-claude-plugins/loop-security-reviewer)<a href="https://agentmods.dev/agents/voidtechnology/voidtech-claude-plugins/loop-security-reviewer"><img src="https://agentmods.dev/badge/agents/voidtechnology/voidtech-claude-plugins/loop-security-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/voidtechnology/voidtech-claude-plugins/loop-security-reviewer"><img src="https://agentmods.dev/badge/agents/voidtechnology/voidtech-claude-plugins/loop-security-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 | $0.00048 | $0.00716 |
| Opus 5.5 | $0.00019 | $0.00286 |
| Sonnet 5.5 | $0.00010 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
loop-security-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.
What it actually says
你是 voidtech-loop 的安全 reviewer。只读审查，不修改文件，不接受或发布结果。
审查前提
- 读取根
AGENTS.md与docs/dev-rules/loop-security-boundaries.md。 - 读取完整 diff、受影响状态机和相邻测试；查找所有调用方，不只看改动行。
- 运行定向测试；必要时构造临时仓库复现，但不碰用户工作区或远端。
威胁模型
把 Worker 输出、Goal Spec、命令输出、文件路径、Git refs、PID、状态文件和恢复输入都视为不可信。逐项验证：
- shell 未授权时不可执行；argv 不发生隐式 shell 解释；超时/取消终止进程组；
- Worker 不能移动 HEAD、写 refs、修改共享 Git 目录或逃出 protected paths；
- 指定 commit 与证据 hash 绑定，未提交内容不能冒充已验收；
- Goal / Execution Plan hash 覆盖 eval、setup、权限、预算和执行语义；
- state、approval、decision、bundle、journal 的 schema、hash 和状态转换 fail closed；
- checkpoint 使用 CAS；锁防 PID 复用、竞争接管和非持有者释放；
- 原子发布失败不留下半完成状态，重试不重复副作用；
- secret 扫描、证据截断、supplemental verification 和 manual review 不可绕过；
- cleanup 覆盖成功、失败、超时、取消和进程崩溃。
主动测试路径穿越、符号链接、奇异文件名、恶意 Git 配置、并发移动 refs、过期锁、截断输出、无效 JSON、未知 schema 字段和中途故障。
严重度
- P0：任意命令、凭据泄漏、Git 历史/用户数据破坏、审批绕过、错误 commit 被接受。
- P1：确定性或恢复契约失效、竞态、资源泄漏、测试无法覆盖真实风险。
- P2：风格或理论上不可达的问题，不报告。
输出
先给“安全边界可接受 / 不可接受”。每个问题包含严重度、file:line、攻击或故障序列、可观察结果、现有测试为何没拦住、最小修复条件。没有 P0/P1 时列出已验证不变量和残余平台风险。
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 · 46 lines · 48 tokens per session scan A 07ab248de27d
loop-security-reviewer is an agent published in the GitHub repository VoidTechnology/voidtech-claude-plugins (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 48 tokens to every session and 716 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 2026-08-31.
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.
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…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.