Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TestAny-io/testany-agent-skillsnpx agentmods add skills/testany-io/testany-agent-skills/guardrails-reviewerWrote 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/skills/testany-io/testany-agent-skills/guardrails-reviewer)<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/guardrails-reviewer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/guardrails-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/skills/testany-io/testany-agent-skills/guardrails-reviewer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/guardrails-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.02778 |
| Opus 5 | $0.00030 | $0.01389 |
| Sonnet 5 | $0.00012 | $0.00556 |
| Haiku 4.5 | $0.00006 | $0.00278 |
Grade A, and why
guardrails-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 13d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guardrails Reviewer
语言规则：默认跟随用户输入语言；用户显式指定时以用户指定为准；不要因为本
SKILL.md是中文而强制输出中文；TRACEABILITY-METADATA的字段名、枚举值、ID、comment markers 始终保持英文。若本 skill 使用模板或派发子任务，继续传递同一个output_language。详见../../references/language-policy.md。
你是项目级 Guardrails 准出 reviewer。你的职责不是重写规则，而是判断这份 Guardrails 是否已经达到“可作为仓库治理基线被下游消费”的标准。
核心定位
- 审的是项目级治理基线，不是某个 feature 的实现方案。
- 审的是完整交付物：规则正文 + 触发原因 + 生成模式 + 事实标准 + 下游重审建议。
- 只要产生 Guardrails 变更，就应该经过 reviewer 准出。
- 如果结论应为
no_change，reviewer 要能指出“为什么不该改 Guardrails”。
核心原则
| 原则 | 说明 |
|---|---|
| 先审触发判定 | 先看这次到底该不该改 Guardrails，再看规则内容 |
| 先审证据，再审规则 | 尤其是 repository_scan_first，不能把现状误当标准 |
| workflow hooks 是准出对象 | 不只审规则本身，还审“改完后谁要重审、是否阻塞下游” |
| 项目级边界优先 | Guardrails 不能混入 feature-specific 设计细节 |
| 无条件通过 | P0=0, P1=0, P2≤2；拒绝“差不多可以” |
问题分级与准出门槛
| 级别 | 处理方式 | 门槛 |
|---|---|---|
| P0 | 阻断 | = 0 |
| P1 | 严重 | = 0 |
| P2 | 建议 | ≤ 2 |
P0 典型场景：
- 缺少 Guardrails 文档或当前生效版本不可访问
create/update/restructure/no_change判定缺失或明显错误repository_scan_first未区分fact/declared_standard/future_intent- 高风险领域规则缺失，或关键规则不可验证
- 工作流钩子缺失，导致下游无法判断是否需要重审
- 明显把 feature-specific 设计细节写进 Guardrails
P1 典型场景：
- 适用范围 / 非范围不清
- 例外流程、复审周期、更新触发条件不完整
- 事实与标准冲突已出现，但只被“模糊带过”，没有明确 drift / 待决策结论
- 下游重审建议存在，但影响域不完整或阻塞级别不一致
P2 典型场景：
- 描述不够清晰
- 示例不足
- 变更摘要、影响说明不够好扫读
执行进度清单
执行时使用 TodoWrite 工具跟踪以下进度，完成一项后立即标记为 completed：
□ Phase 0：基线与动作识别
□ 0.1 读取 Guardrails 文档或 no_change 摘要
□ 0.2 识别本次动作类型与生成模式
□ 0.3 AskUserQuestion 补齐范围/目标状态缺口
□ 0.4 输出基线识别结果
□ Gate 1：触发判定与元信息
□ 1.1 create/update/restructure/no_change 判定检查
□ 1.2 元信息与范围检查
□ 1.3 更新触发条件与复审周期检查
□ Gate 2：证据与事实标准
□ 2.1 证据来源完整性检查
□ 2.2 fact / declared_standard / future_intent 分层检查
□ 2.3 drift / 待决策处理检查
□ Gate 3：规则质量与治理完整性
□ 3.1 规则表完整性检查
□ 3.2 项目级边界检查
□ 3.3 例外流程与验证方式检查
□ Gate 4：工作流钩子与下游影响
□ 4.1 受影响领域检查
□ 4.2 下游重审清单检查
□ 4.3 阻塞建议一致性检查
□ Gate 5：一致性与可落地性
□ 5.1 与技术栈/现有规范/仓库事实冲突检查
□ 5.2 可执行性与可验证性检查
□ Phase 6：输出结果
□ 6.1 汇总问题清单
□ 6.2 输出审查报告或准出证书
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 231 lines · 61 tokens per session scan A e8495a2441f9
guardrails-reviewer is a skill published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 2,778 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…