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-managernpx skills add BuildrAI/Buildr --skill task-managergit clone --depth 1 https://github.com/BuildrAI/BuildrWhat 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 | $0.00087 | $0.01573 |
| Opus 5 | $0.00044 | $0.00787 |
| Sonnet 5 | $0.00017 | $0.00315 |
| Haiku 4.5 | $0.00009 | $0.00157 |
Grade A, and why
task-manager 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 3d ago.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Manager Skill
本 Skill 是 buildr.task-record/v2 的默认 provider，只管理 Task 的最小顶层记录、直接 Parent/Child 和复盘来源。todo 是已接受但未启动的 data-only 意向，active 才进入正式执行。Buildr Web 是同一 Application 的独立人类客户端；Parent Plan、Contribution、复盘正文和专业事实不得复制到 Task Record。
Parent/Child只表达真正独立交付的协调层级。普通Agent并行调查、临时分工、同一交付内的局部实现或测试协作不触发本Skill创建Child；只有工作能单独说明目标/scope并形成Candidate/evidence、immutable Handoff与真实Delivery时，才建立正式Child关系。
1. 何时使用
仅在以下意图使用：
- 用户明确创建、查看、修改、激活、设置或清除 Parent、维护复盘来源、完成或放弃 Task Record；
- 用户给出 Task ID 要求继续正式任务，需要先恢复 title、intent、scope、Change 引用和顶层状态；
task-triage已判断即将进入正式持久交付，并在首次交付写入前要求创建或恢复记录。
不要仅因用户说“任务”就触发。普通任务分流、讨论、只读探索、单次测试、临时服务、只维护已有 metadata，以及 Task Environment、Development、Review、Verification、Git、Finish、Board 或 Retrospective 动作都不由本 Skill 执行。
2. 输入与 canonical target
确认 operation、稳定小写 Task ID、canonical Workspace 和明确字段。create 默认 active；只有用户已接受意向但尚未授权执行时使用 --status todo。todo 不得带 Change，也不运行 Git、Environment 或专业动作。复盘来源可在 create 或 update 中重复提供，但每个来源必须是已有 current 复盘的 completed/abandoned Task；只保存 source Task ID，不保存行动项或报告副本。activate 仅做 todo-to-active，调用前置门禁由 task-triage 负责。complete 需要 summary 和明确 no-change，todo 只允许 no-change；abandon 需要 reason。
当前位于 task environment 时，只接受上游已确认的 canonical Workspace target；不读取 environment receipt，不扫描父目录，不从 worktree 推断 retained root，也不把 environment identity 写入 Task Record。Buildr Web 已创建或用户按 Task ID 继续时先 inspect，同一记录即为权威来源。
作为 Buildr Web 统一内部文档引用规则在 Task intent 的具体应用：引用已登记 Project 内的 Markdown 文档时，使用具名的 Workspace 相对 Markdown 链接，例如 [方案名称](projects/<project>/docs/<document>.md)；不要只写裸路径、本机绝对路径或 file: URL。写入后确认 Buildr Web 将其呈现为可点击引用，并区分“链接可解析”与“正文当前可读取”：文档尚只存在于 Task Environment 时应如实说明暂不可预览，不得复制正文到 Task Record 或声称 canonical Project 已包含该文档。
3. 执行动作
调用 selected provider 对应的产品命令：
buildr task create <task-id> --title <text> --intent <text> [--status todo|active] [--retrospective-source <task-id> ...] [--parent <task-id>] [--project <code> ...] [--service <project/service> ...] [--change <project/change> ...] --target <canonical-workspace> --json
buildr task inspect <task-id> --target <canonical-workspace> --json
buildr task update <task-id> [--add-retrospective-source <task-id> ... | --remove-retrospective-source <task-id> ...] [--parent <task-id> | --clear-parent] [set/add/remove flags] --target <canonical-workspace> --json
buildr task activate <task-id> --target <canonical-workspace> --json
buildr task complete <task-id> --summary <text> [--no-change] --target <canonical-workspace> --json
buildr task abandon <task-id> --reason <text> --target <canonical-workspace> --json
What ships with it
1 file 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.
- 3d ago First seen · 56 lines · 87 tokens per session scan A f08eb1dc941d
task-manager is a skill published in the GitHub repository BuildrAI/Buildr (24 stars, last pushed 3d ago), licensed MIT. It adds 87 tokens to every session and 1,573 once invoked, about $0.0004 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…