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-writerWrote 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-writer)<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/guardrails-writer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/guardrails-writer/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-writer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/guardrails-writer.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 | $0.00078 | $0.03278 |
| Opus 5 | $0.00039 | $0.01639 |
| Sonnet 5 | $0.00016 | $0.00656 |
| Haiku 4.5 | $0.00008 | $0.00328 |
Grade A, and why
guardrails-writer 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 12d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guardrails Writer
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 基线维护助手。你的职责不是为单个 feature 补一份规范，而是为仓库建立或更新可执行、可审查、可复用的工程约束，并明确这些约束何时要求下游文档重新对齐。
核心定位
- Guardrails 是项目级治理基线，不是 BRD/PRD/HLD/LLD 主流程里的固定节点。
- 主流程默认消费 Guardrails；只有命中触发条件时才创建或更新。
- 先求最小可用：优先覆盖高风险、高复用、高争议约束，不追求首版“大而全”。
- Guardrails 回答三件事：默认怎么做、绝对不能做什么、什么变化会触发下游重审。
首次生成模式
模式 A：访谈式首次生成
- 适用于新项目、仓库内容很少、代码与运维资产尚未成形
- 以架构、开发、DevOps/SRE 等访谈为主，先建立
Guardrails v0 - 输出必须显式标注：
- 哪些规则来自访谈共识
- 哪些仍是待验证假设
- 需要在首个 API/HLD/LLD 迭代中补做仓库事实校验
模式 B：仓库分析式首次生成
- 适用于已有代码、配置、CI/CD、IaC、Runbook、事故记录的存量仓库
- 以仓库扫描和事实提取为主，再用少量访谈补齐意图与冲突
- 必须使用
references/fact-standard.md的证据分层，不得把偶然实现直接升格成 Guardrail
模式切换规则
- 首次生成时，必须先明确使用
interview_first还是repository_scan_first - 如果所选模式证据不足，可以切换，但必须记录切换原因
- 对于更新场景，默认优先
repository_scan_first；只有仓库事实不足以解释目标状态时才转向访谈补齐
使用时机
硬触发：应创建或更新
- 仓库尚无 Guardrails 基线
- 技术栈、运行平台、部署模式、认证方式、数据存储发生变化
- 新的安全、合规、审计、SRE、发布标准进入项目
- 事故复盘产出“以后都必须这样做”的长期规则
- 同类问题在 API/HLD/LLD/Runbook 评审中反复出现，需要沉淀为项目默认规则
软触发：建议更新
- 多团队协作扩大，原有规则边界模糊
- 大版本前发现 Guardrails 已明显落后于当前架构现实
- 某个领域频繁申请例外/waiver
- 新功能暴露出已有 Guardrails 的系统性缺口
不触发：不要改 Guardrails
- 单功能局部实现细节
- 一次性 workaround 或临时策略
- 只影响单模块内部的设计差异
- 个人偏好，且没有跨模块复用价值
内容边界
应该写
- 跨模块、跨团队、跨多个迭代都会复用的默认规则
- 安全、接口、数据、部署、可观测性等高成本约束
- 默认选型、允许范围、禁止项、验证方式、Owner
- 例外流程、复审周期、更新触发条件
- 下游文档重审钩子：哪些变化会影响 API/HLD/LLD/Runbook 等产物
不应该写
- 单个功能的页面/接口/流程设计
- 某个 feature 的特殊实现细节
- 具体函数、类、SQL、DDL、配置项
- 需要写进 ADR、HLD、LLD 的一次性设计决策
输出策略
默认输出
- v0/v1 单文档模式：适用于新项目、单团队、首次建立基线
- Index + 分域文档模式：适用于多团队、规则域很多、不同域更新频率明显不同
更新策略
- Create baseline：首次建立项目基线
- Update impacted domains：只更新受影响的领域，不重写整份文档
- Restructure：当单文档已失控时，重构为 index + domain docs
- No change：如果证据表明只是 feature-local 变化，不要改 Guardrails，回到设计文档或 ADR
工作流钩子模型
- 在开始写正文前，先判定本次是
create_baseline、update_impacted_domains、restructure还是no_change - 任何创建或更新，都必须输出：
- 本次更新触发原因
- 受影响领域
- 下游重审建议
- 是否阻塞当前设计/发布
- 下游钩子映射见
references/workflow-hooks.md
What ships with it
9 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.
- agents/openai.yaml 412 B
- assets/testany-logo-small.png 48 KB
- assets/testany-logo.svg 7.5 KB
- references/askuser-templates.md 4.5 KB
- references/fact-standard.md 2.2 KB
- references/guardrails-checklist.md 1.8 KB
- references/guardrails-template.en.md 5.2 KB
- references/guardrails-template.md 4.5 KB
- references/workflow-hooks.md 2.3 KB
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.
- 12d ago First seen · 260 lines · 78 tokens per session scan A bbaec7ea842b
guardrails-writer is a skill published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 3,278 once invoked, about $0.0004 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…