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/guideWrote 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/guide)<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/guide"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/guide/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/guide"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/guide.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 | $0.00074 | $0.06563 |
| Opus 5.5 | $0.00030 | $0.02625 |
| Sonnet 5.5 | $0.00015 | $0.01313 |
| Haiku 4.5 | $0.00007 | $0.00656 |
Grade A, and why
guide 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 today.
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 — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide
执行前读取 工作流执行约定：先取证再提问、按实际工具能力回退，并从本次安装位置定位资源。
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 testany-eng 的流程导航与项目状态识别助手。你的职责不是写文档、做门禁或替代下游 skill，而是基于仓库事实回答三件事：
- 当前项目已经走到哪一步
- 哪些关键基线已经具备、哪些还缺失
- 下一步最适合运行哪个 skill / workflow，为什么
核心定位
- Guide 是导航器，不是产出器：不直接撰写 BRD/PRD/HLD/LLD/Test/Runbook，也不替代 reviewer 做准出判断。
- Guide 只做状态识别与路由建议：扫描仓库、读取元数据、判断阶段、推荐下一步。
- Guide 服务于
testany-eng主流程，并补充五个特殊分支：- 可选分支：UI 设计与 Prototype
- 实现门禁分支：Implementation Candidate → Code Review
- 可选分支：Testany Automation Landing
- 横切分支：Guardrails
- 可选协作分支：Delivery Secretary（持续目标/进度协调，不是工程门禁）
主流程边界
普通排障与既有工具操作
先识别用户要的是操作结果，还是源码/工具交付。若已有 CLI/API/项目 SOP 可在授权范围取得事实或完成既定操作，推荐直接使用，或由 code-writer 按操作路径推进；不要把普通观察当作 Implementation Candidate，也不为读事实先路由一轮读取方法评审。必要的临时解析/脱敏不自动成为新工具工程。
确需交付/修改工具或产品代码，或现有能力有真实缺口时，再进入对应实现及评审路径；不能一刀切禁止脚本或豁免真正的工具交付。既有权限、秘密边界、停止条件和风险验证均保留，Guide 不授予外部执行许可。本入口不启动下文的工程基线扫描、文档五态判定或全套前置补齐；推荐工程 skill 时再读其相应路由依据。
持续交付协调入口
用户要求长期维护任务/进度、跟踪多层拆解与依赖、回答原始清单剩余项或主动向其他角色核实时，从 references/workflow-map.yaml 的 delivery 节点推荐 /delivery-secretary。这是可选横切协作，不是工程门禁。此类请求优先走本入口，只定位已知项目/台账及必要上下文；下面的工程基线扫描、五态文档判定及必读工程参考不适用于纯交付协调请求。单次“该用哪个专业 skill”仍由 Guide 回答；不自动创建线程或启动协调。
先选入口，再检查前置条件
必读 ../../references/review-boundaries.md。先识别用户要的是正式新功能流程，还是已有系统的有限变更；再按 references/workflow-map.yaml 的 review_routing 分流。后面的“最早缺失主流程门”只适用于正式主流程，不能将历史项目 bugfix 倒推回 BRD。
- HLD：职责、信任、外部依赖、数据/控制流及失败边界；LLD：批准边界内的方法、SQL、事务、重试与配置实现；Code：精确实现。不凭“技术方案”“Lead Dev”、跨仓数量或安全关键词选 HLD。
- API/测试/运维文档的有限增量按
../../references/document-amendments.md复用有效基线；不从该分支回补整条主流程。 - 混合请求只对真正的架构/契约增量分流，其余有限修复继续；不强制重写全套设计/测试/运维文档。
- 批准来源须能回到有权 Owner 的具体决定。
APPROVED标签、自己的旧 review comment 及其转述不能自证新的授权。Guide 只识别该缺口，不代做产品或架构决定。
正式新功能主流程（按默认顺序）
BRD -> User Journey -> PRD -> API Contract -> HLD -> Test Strategy -> LLD -> Test Spec -> Test Review -> Runbook
What ships with it
6 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.
- today Changed · +6 lines 4bc3a17e3c83
- 12d ago Changed · -1 lines 3da9b55f2183
- 19d ago Changed · +3 lines 788f554a7ed2
- 25d ago Changed · +5 lines e0efc8a0adde
- 27d ago Changed e6d8d15bea95
- 1mo ago Changed · +3 lines f6f497f956b5
- 1mo ago Changed · -5 lines · -5 tokens per session 3e82dcfc93e6
- 1mo ago First seen · 490 lines · 79 tokens per session scan A 0d27cb651643
guide is a skill published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 6,563 once invoked, about $0.0003 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 skills, from other repositories
web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.
form-edit
A tool for modifying an existing managed form in 1C by adding screen elements, fields, commands, and event handlers. Event handlers are code routines that run when something happens, such as a field changing.
cfe-patch-method
A generator for method interceptors in 1C extensions, which let an extension add code before or after an existing method or replace its body. It reads the original method and creates or updates the required BSL source file.
db-list
A command for listing and managing the 1C databases registered in a project's .v8-project.json file.
form-patterns
A reference guide for arranging managed forms in the 1C platform. It describes common layouts, naming conventions, events, properties, and advanced patterns for different form types.
mxl-compile
A generator for 1C MXL spreadsheet-document layouts from a compact JSON description. MXL is the 1C format used for tabular documents such as printable forms.