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 BuildrAI/Buildr --skill task-verificationgit clone --depth 1 https://github.com/BuildrAI/BuildrWrote 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/buildrai/buildr/task-verification)<a href="https://agentmods.dev/skills/buildrai/buildr/task-verification"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/task-verification/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/buildrai/buildr/task-verification"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/task-verification.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 | $0.00032 | $0.01696 |
| Opus 5.5 | $0.00013 | $0.00678 |
| Sonnet 5.5 | $0.00006 | $0.00339 |
| Haiku 4.5 | $0.00003 | $0.00170 |
Grade A, and why
task-verification 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 yesterday.
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
任务验证
本技能(Skill)是 buildr.task-verification/v4 的默认提供者。项目拥有测试代码、替身(fixture/mock)、构建脚本和环境;智能体(Agent)选择并调用 Maven、Gradle、npm、Playwright、Browser、HTTP 等真实工具。Buildr 只维护项目测试地图和开发完成后的任务验证报告,不生成计划或统一运行测试。
按本次目标进入
| 目标 | 读取与动作 |
|---|---|
| 选择已有检查 | 核对任务目标、真实改动和相关项目测试地图,按下节选择与执行;遇到服务绑定、外部代码库或位置诊断时读路径根与声明字段 |
| 维护测试地图 | 读地图写入步骤,依据实际构建、测试、脚本、持续集成(CI)和团队边界维护少量稳定测试体系;不在地图中逐项登记测试文件 |
| 查看或登记已有报告 | 读报告登记步骤;查看只执行 inspect,登记先核对已有结果适用性,不因登记重新调查测试体系或运行检查 |
项目测试地图位于 projects/<project>/verification.yml,使用 buildr.project-verification/v4。只选择检查或登记报告时不加载地图写入步骤;缺少测试时交给 project-testing 在实际改动范围内补齐,不在本技能中生成框架或测试。
选择与执行已有检查
先从 task inspect 的 record.brief 读取任务说明(Task Brief),对照其中的目标、必要范围、风险和完成依据决定需要哪些真实证明;独立于方案审查(Planning Review)、实现审查(Implementation Review)以及是否采用 OpenSpec。没有变更(Change)不代表无需验证,审查通过也不替代验证。确实不适用时通过工作摘要(Work Context)的 checks 结论显式留痕本次事实理由(task work-context record --check verification --check-status not-applicable --check-reason <理由>),不只留在对话或临时文本中;需要但未完成、没有报告、未执行或材料缺失不能写成不适用或已通过,不生成占位报告。
从改动追踪到用户实际使用的交付物(Artifact),核对受影响的公共行为、构建与资源依赖、安装或部署后入口及平台差异。先判断已有检查的内容、环境、目标和覆盖范围是否仍适用;复用有效结果,只补充新改动、失败或明确未解决风险所需的检查。保留原执行事实并说明复用依据,无法确认适用性的历史结果不作为当前成功证据。
需要执行时,智能体(Agent)直接调用项目工具。执行地图入口前重新读取当前地图的 locations 及根目录适用规则,在对应 ready 位置按声明的 argv 与解析后的 cwd 调用,保留项目拥有的包装命令(wrapper),不得简化为系统 PATH 上的裸 node 或 npm;kind: agent 按真实根和指引选择工具。路径根、服务范围和位置诊断的解释见声明字段。unavailable 只表示该族当前目录不可用,说明局部缺口并继续其他可执行检查,不使有效地图或已有真实结果失效。
优先运行相关检查。纯文档改动只选实际受影响的链接、渲染、资源引用或敏感信息检查,不默认捆绑编译、整组单元测试、架构或规范检查;文档确为可执行输入时保留其真实消费方验证。扩大到完整回归应有改动影响或明确未解决风险作为依据,不能只以默认组合或阶段名称解释;环境冒烟仅在目标适用、环境可用且已获授权时执行。必要的构建、安装后功能和平台检查应在开发完成前执行,不能仅因被归类为发布检查而推迟;优先复用真实入口和隔离环境,外部副作用仍遵守原有授权。
自动选择结果、测试名称、位置可用和命令成功都不能替代覆盖判断。完整入口必须覆盖测试族声明的范围;发现缺少测试、入口失配或漏选时,在授权范围内调整声明,或交给 project-testing 补齐并验证。运行中不改被验证源码,一次收集可独立执行的失败后集中报告;真实依赖阻塞的下游列为未执行。处理失败前先审视检查价值,按已有授权修复后只补失败与实际受影响的检查,不自动整套重跑。
开发中的临时反馈不写任务验证报告(Task Verification Report),不创建 Buildr 计划(Plan)、执行(Run)、执行记录(Execution Record)或流程状态。
What ships with it
5 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.
- yesterday Changed · +2 lines 6dab195569a5
- 5d ago Changed b9811e345fa9
- 9d ago Changed · +2 lines b764cd62c824
- 28d ago Changed · +4 lines 7559190459e9
- 1mo ago Changed 79aecda39c31
- 1mo ago Changed · +4 lines 9f96b39189f1
- 1mo ago Changed · -23 lines · -29 tokens per session d2ad0aa5083e
- 1mo ago Changed e35d3a0c9aa4
- 1mo ago Changed · -116 lines · -17 tokens per session cc4c671394cd
- 1mo ago First seen · 176 lines · 78 tokens per session scan A 80350837a9fc
task-verification is a skill published in the GitHub repository BuildrAI/Buildr (28 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,696 once invoked, about $0.0001 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.