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.
npx skills add TestAny-io/testany-agent-skills --skill code-writergit clone --depth 1 https://github.com/TestAny-io/testany-agent-skillsWrote 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/code-writer)<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/code-writer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/code-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/code-writer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/code-writer.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 | $0.00104 | $0.02841 |
| Opus 5.5 | $0.00042 | $0.01136 |
| Sonnet 5.5 | $0.00021 | $0.00568 |
| Haiku 4.5 | $0.00010 | $0.00284 |
Grade A, and why
code-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 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Writer — 实现与工程续接
完成当前授权范围内的操作、根因排查或实现及必要验证。确需交付或修改源码/工具时，形成可独立评审的精确 Candidate；使用已有工具完成操作时，交付实际结果与限制。效率来自复用仍有效的判断和证据，不来自少查问题或降低门禁。
输出语言跟随用户；机器字段与 ID 保持英文。只需修小问题时直接完成，不创建无关流程工件。
先区分操作与实现
- 用户需要当前事实、具体错误或既定操作结果，且已有 CLI/API/项目 SOP 能在授权范围完成时，直接使用它们。可用少量临时命令/脚本解析、脱敏；不因使用了 shell/Python 就变成工具开发，也不为普通排障先造 reader、代理或源码 Candidate、排读取方法评审。完成以目标事实/实际结果为准，不以工件齐全为准。
- 用户确实要求可复用工具/代码交付，或现有能力不足且已明确实现范围时，才走工程实现与原源码审查。允许有实际用途的小脚本；不能把有用工具一律禁止，也不能把真正工具交付称作“只读”来免审。
- 两条路径都不扩大权限或秘密边界。命令失败先看实际调用、退出码与必要且安全的底层错误，区分参数/parser错误和环境问题，不能把失败/未取到数据当成不存在。按原授权、停止/重试约定与风险验证继续；新写入或范围缺口不因分流自动获准，普通操作也不新增一层审批/核收。
入口与恢复
先遵守目标仓库的 AGENTS/README 和相关约束，读取当前请求、批准基线与实际变更。局部修复使用已有边界，不因为启用本 skill 就补写全套设计。新增产品承诺、接口/信任边界或未批准架构面时转对应 Owner/专业 skill；已授权实现细节由 Writer 自主推进。
本 skill 随 完整 testany-eng 插件发布；公共脚本和参考从此 SKILL.md 的实际目录向上两层解析。需要使用这些脚本时，在首次使用、安装更新或发现依赖错误时核对资源：本次 resume/bind/locate 已内置检查，无需先另跑 check；使用其他公共脚本且尚未核对时才运行 python3 <plugin-dir>/scripts/workflow_context.py check。同版本正常工作无需逐轮检查；普通操作未使用这些脚本时不为此先跑资源检查。缺少资源时恢复整包安装，不能依赖源仓库或另一个旧版本缓存补洞。
跨压缩、会话或阶段的长任务，首次接入按 持久入口 将角色、当前任务和已有工程记录位置绑定到稳定入口，并在项目的宿主入口（如 AGENTS.md）留下短引用。此配置随项目使用，技能通用实现随插件发布；不把具体项目路径、线程 ID 写进插件。
恢复遵循下面的顺序；当前上下文充分时直接工作，不为流程而重读：
- 当前请求先于旧记录。 区分同一任务续接、正常支线、新 Candidate、新反证或批准撤回。任务已切换时明确新任务标识；不能把入口里旧的 task ID 当成用户当前目标。
- 从当前可信摘要/工程记录保留的问题与判断、binding、有效结果、未闭合事项、下一步和证据引用继续。需要磁盘恢复且已知入口/当前 task 时，直接执行下方
resume，不先locate、读状态目录或重读持久入口说明；说明仅在接入、切换绑定或排除相应错误时查。已知只缺哪些字段时重复--field合并读取。TARGET_MISMATCH必须修正任务绑定，不能悄悄使用旧状态。 - 检查新事实导致的失效范围，只补缺失的规则、源码与证据。
resume在总预算内完整返回核心字段；过长字段按返回参数续读：下一次 argv =continuation_prefix（若有）+ 该字段的next_args，交给同一工具，不猜 pointer、depth 或预算。PARTIAL/缺失不是无问题或已读；来源变化则重新恢复受影响内容，不拼接旧段。package 摘要变化才重新加载相关 skill；“读过 skill”不等于工具已运行、进度已落盘或质量已验证。 - 实质交接、当前目标/Candidate/结论变化时，更新原工程记录的工作位置；入口位置变化时同步
bind。普通进度回复不逐轮 checkpoint。正常暂停任务保留各自位置，切回时使用其精确记录，关闭项的详细历史留在原证据中。
python3 <plugin-dir>/scripts/workflow_context.py resume \
--entry <已登记入口> --role writer --task <当前请求对应的task-id>
What ships with it
2 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 · +10 lines · +6 tokens per session eed706ef9300
- 18d ago Changed · +7 lines 2aac9f8b054a
- 19d ago First seen · 63 lines · 98 tokens per session scan A 414270b844bd
code-writer is a skill published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 2,841 once invoked, about $0.0004 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 2026-10-05.
Other skills, from other repositories
qa-expert
Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.
bug-analysis
A method for investigating confirmed software bugs by tracing their cause in code and assessing their effects. It also records repair and regression-testing recommendations in a test report.
Flaky Test Analyzer
Skill phân tích và khắc phục các automation test không ổn định (flaky tests), xác định root cause và đề xuất fix.
Locator Healer Agent
Skill tự động phát hiện và sửa chữa locators bị hỏng khi automation tests fail do thay đổi DOM.
writing-nemesis
Guides writing new nemesis (chaos engineering disruptions) for the SCT framework. Use when creating a new NemesisBaseClass subclass, adding disruption logic, setting nemesis flags, or configuring target node pools. Covers the sdcm/nemesis/ package structure, auto-discovery, flag filtering, CI configuration, and unit…
qf-fix
Analyze failing tests from the last /qf-run and fix the source code to make them pass. Use when the user runs /qf-fix, asks to "fix failing tests", or asks to "fix test failures". Requires result files from a prior /qf-run.