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 agentmods add skills/buildrai/buildr/task-finishnpx 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.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01216 |
| Opus 5 | $0.00026 | $0.00608 |
| Sonnet 5 | $0.00011 | $0.00243 |
| Haiku 4.5 | $0.00005 | $0.00122 |
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.
What it actually says
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。智能体(Agent)依据目标、现场与已有授权持续推进,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 |
先核对目标、实际仓库或业务对象、成果归属、交付位置和授权。已选择的能力提供者继续适用;有匹配任务时用 task inspect 读取当前结果与版本,目标完成后用 task complete --expected-record <recordDigest> 保存真实摘要和 noChange,明确采用刚读到的记录版本,冲突后重读。记录完成不等于机器证明已交付。没有匹配任务就继续实际工作,不补建记录。
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;按约定提交、集成与普通推送,回读实际目标。非 Git 成果检查实际业务结果,不能只看请求成功。已成立的成果不重复交付,多仓分别保留结果。
按需读取
- 上下文中已读且仍适用的规则、技能和入口直接复用;缺失或更新时补读。任务版本及 Git 状态仍在写入前重验。
- 已知路径和命令直接使用;未知入口先定位文件或查帮助,再读取相关部分。
- 大结果先提取状态、诊断和必要证据,缺口再展开。截断输出不作完整 JSON 解析,不因输出不全重跑有副作用的动作。
具体检查
- 写入前: 对象、版本、归属、授权和实际影响范围明确。
- 写入后: 回读交付位置及业务结果,不能把命令成功等同于目标完成。
- 删除前: 核验资源归属、未保存内容和成果仍被保留。有受管资源时交给原所有者,无需重新准备完整环境。Git成果已完整核验交付后,向
task environment cleanup成对传递逐仓--expected-source <selector>=<完整源提交>与--delivered-ref <selector>=<完整交付提交>,继续删除工作树和本地任务分支;输入来自实际Git结果,不建证明文件,不把completed或目标提交存在当作完整交付。清理拒绝源变化或未保存内容时,只核对其具体差异,不重新交付已成立的成果。 - 内容检查: 先判断本次集成是否改变已有验证覆盖的内容或相关运行条件。没有改变就复用结果,不因收尾、重新生成提交或提交编号变化追加测试。冲突处理、其他集成修改或已知问题确实影响行为时,只选择覆盖实际影响的最小充分已有检查,并在推进目标分支前执行且通过,再集成推送。选择依据是风险与运行成本,不是测试条数;没有检查过就如实报告。
上述检查保护具体动作。收尾不通过 task next,不建立候选、研发交接、旧收尾运行、统一验证记录或新的证明文件;不因一句收尾重跑全量测试、全局诊断或完整审查。需要修正成果时,在授权内完成修正及其相关检查,再交付受影响部分。
失败与完成
已知、必要、已获授权且安全的后续动作继续完成,不把可执行工作留作建议。必要成果未交付不能标记整个目标完成;清理或可选激活失败不撤销已交付成果。登记失败只修复或重试登记,不重推业务内容。
保留未知归属、未交付内容、共享缓存、凭证和业务数据。普通收尾不授权强推、丢弃内容、覆盖他人工作、改写共享历史、删除远端分支或替用户选择语义冲突。只有需要扩大授权或业务取舍时提出最小问题。
结束时简述成果与位置、检查及限制、已有任务结果、资源已处理或保留的情况。适用的部署、发布、自举由原专业能力独立承担;普通工作空间不触发 Buildr 自举。
父任务完成遵守 task-manager 的明确授权与总体验收边界。子任务收尾不授权完成父任务;整体目标已核对但尚无明确授权时,报告验收结果并保持父任务状态,不补造授权。
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 · -28 lines · -23 tokens per session bcff18987454
- 5d ago First seen · 75 lines · 76 tokens per session scan A 567f74e7b7cf
task-finish is a skill published in the GitHub repository BuildrAI/Buildr (24 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,216 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…