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-finishgit 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-finish)<a href="https://agentmods.dev/skills/buildrai/buildr/task-finish"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/task-finish/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-finish"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/task-finish.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 | $0.00062 | $0.03290 |
| Opus 5.5 | $0.00025 | $0.01316 |
| Sonnet 5.5 | $0.00012 | $0.00658 |
| Haiku 4.5 | $0.00006 | $0.00329 |
Grade A, and why
task-finish 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
收尾与交付
日常表达中的“收尾”和“交付”都可以表示本轮工作完成后的结束动作;用户明确要求时即触发本技能(Skill)。该指令本身是当前任务范围内常规 Git 提交、集成和普通推送的明确授权,不要求用户再逐项重复。智能体(Agent)依据目标与现场持续推进,直到成果到达约定位置、已有任务结果登记、可安全处理的资源已处理,并交代遗留事项。部署或发布只有明确属于目标且已获授权时才执行。
按实际对象组合
| 现场 | 应完成的工作 |
|---|---|
| 有 Buildr 任务,无 Git | 使用实际业务工具交付成果,登记已有任务结果,处理相关资源 |
| 无 Buildr 任务,有 Git | 按约定提交、集成、普通推送并回读,不补建任务 |
| 两者都有 | 完成 Git 交付、已有任务登记和相关资源善后 |
| 两者都没有 | 完成成果本身需要的交付,不制造记录或提交 |
已确认的非 Git 资料按所属专业工具交付,并从实际目标回读正文、来源和必要结果;旧观察冲突时保留当前内容,不以任务记录成功替代成果验收。Git 提交、远端查询与工作树(Worktree)清理只针对本任务实际存在的 Git 对象;纯非 Git 工作不制造这些动作或证据,混合范围逐对象处理。
承接当前对话中已确认的目标、成果、执行位置、验证及授权,复用仍适用的技能(Skill)和能力提供者(Provider)。缺少上下文或发现变化时,只补读相关部分。有匹配任务时取得当前记录与 recordDigest,完成后用 task complete --expected-record <recordDigest> 保存实际结果;可以使用刚读取或前一步成功写入返回的版本,冲突后重读。没有匹配任务就交付实际成果,不补建记录。
将当前任务的常规 Git 授权连同已核验的 operation、对象、目标、范围和效果交给所选 git-operations 提供者(Provider),不让提供者重新索取同一授权。每次 Git 写入前核对真实仓库、分支、远端、暂存及未跟踪内容和完整推送范围,只纳入本轮成果;在目标和安全集成方式明确时按约定提交、集成与普通推送,回读实际目标。无法唯一确定对象、目标或完整范围时停止受影响的写入,不以“收尾”猜测。非 Git 成果检查实际业务结果,不能只看请求成功。复用已经成立的交付事实,多仓分别保留结果。
有明确正式任务(Task)且需要创建提交时,同时把已核验的任务编码交给 git-operations,由其按提交说明(Commit Message)约定写入唯一 Buildr-Task 尾注(Trailer),回读真实提交并通过 task commits 确认任务侧关联;复用它返回的实际代码库(Repository)、完整哈希值(Hash)、说明和读取诊断,不重复执行提交。没有任务时省略关联,不补建任务。提交成功但关联查询失败或未覆盖时,分别说明交付事实与尚未确认的关联,不因此改写历史、撤销任务结果或阻断其他安全收尾;关联存在也不能替代成果验收与交付核验。
核对必要任务材料
已有正式任务时,依据任务记录(Task Record)的当前 brief、完成依据和实际材料需要,分别核对说明保存、项目成果交付、其他材料引用与用户实际节点可读性。由 task-manager 接续正文及必要方案、实施、交付引用;不强制长模板,不默认将过程报告收纳到知识目录,也不把专业结果复制进说明。
复用有效读取事实;说明变化时通过 task inspect 核对当前 brief 与 recordDigest,其他材料变化时通过 task materials inspect 核对文件、来源和摘要。说明随任务数据库保存,本机清单及正文不随 Git 推送;项目材料在候选工作树(Worktree)中时如实说明,交付后核对约定位置。实际从任务列表打开详情并刷新,确认说明节点读取记录中的当前正文;链接可打开、代码已推送或任务已完成均不能代替这个观察。已有适用节点检查可复用,无法核对时如实报告未覆盖。
旧说明只在已授权范围内使用 task brief migrate 显式导入,保留原文件与历史;空正文不能回退旧文件或变更说明。正文或材料缺口局部处理,不将缺少报告升级为统一门禁;目标所需成果、检查或交付未完成不得报整体完成。真实审查与验证在任务仍为 active 时保存,不等终态后补写。变更(Change)归档只移动自身材料,不移动或删除记录正文;本机材料清理不自动完成任务或删除工作树。
常规收尾
成果已完成、验证仍适用、交付目标明确且没有待解决冲突时,直接组合下列动作。按实际对象省略不适用项,依赖前一步结果的动作顺序执行。
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 · +1 lines e454266b146a
- 5d ago Changed e01e4e87bc06
- 9d ago Changed · +10 lines 21a81d373f31
- 25d ago Changed · +13 lines c658e7e2a3bf
- 1mo ago Changed · +9 tokens per session c419da650dcc
- 1mo ago Changed · +7 lines 039ab6d168ba
- 1mo ago Changed · +2 lines 738d046b3d44
- 1mo ago Changed · -28 lines · -23 tokens per session bcff18987454
- 1mo ago First seen · 75 lines · 76 tokens per session scan A 567f74e7b7cf
task-finish is a skill published in the GitHub repository BuildrAI/Buildr (28 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 3,290 once invoked, about $0.0002 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.