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-managergit 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-manager)<a href="https://agentmods.dev/skills/buildrai/buildr/task-manager"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/task-manager/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-manager"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/task-manager.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 | $0.00060 | $0.05929 |
| Opus 5.5 | $0.00024 | $0.02372 |
| Sonnet 5.5 | $0.00012 | $0.01186 |
| Haiku 4.5 | $0.00006 | $0.00593 |
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 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
任务管理
本技能（Skill）提供 buildr.task-record/v4：管理短目标、任务说明正文、范围、直接父子关系、独立状态、结果，以及本机复盘文档摘要和人的决定状态。任务记录通过产品动作维护，不直接编辑数据库。
开始或继续授权工作
用户说“先修复”“按方案优化”“继续做”，且已授权交付代码、文档、配置、规则（Rule）或技能（Skill）的持久修改时，默认在首次交付文件写入前登记或接续任务；小改动也适用，不要求用户另说“创建 Buildr 任务”。登记只维护工作事实，后续分流、隔离、实施和交付仍交给对应专业技能（Skill）。
先核对当前对话、已提供任务标识与可用任务公开读取结果中的目标和范围。匹配已有任务就读取并接续；todo 按已观察版本激活，active 复用，终态不自动恢复。确认没有匹配任务时创建一个 active 任务。同名不同目标先区分归属；工作树（Worktree）存在不证明任务记录存在。不因换轮次或阶段转换重复创建，也不为旧任务补造开始历史。
纯只读咨询、诊断、讨论方案，尚未授权实施的建议，以及仅修改已有任务记录或维护其生命周期时，不另建任务；明确接受但尚未启动的待办继续使用 todo。用户明确要求不登记时尊重其范围，不把默认做法变成新的授权要求。
登记成功后，在形成可接续的进展、决定、阶段变化或结果时，按下文维护工作摘要（Work Context）和真实任务结果；不逐工具调用记日志，不把“已登记”当成业务完成。记录提供者不可用或写入冲突时报告具体缺口，停止对应记录写入，保留现场并继续可独立的只读检查与有界测试；不手写数据库或伪造任务成功。
Codex 原生会话与任务关联
用户在具体 Codex 会话中给出任务编号并要求关联时，直接核对目标工作空间（Workspace）和任务（Task），由当前会话直接执行命令读取 CODEX_THREAD_ID，再调用显式关联动作。用户的这条指令就是关联授权，不要求先去网页创建请求或打开面板二次确认。任务编号只在所属工作空间内定位，多个工作空间存在同编号时不能猜测。
buildr codex link --target <canonical-workspace> --task <task-id> --native-session-id <direct-CODEX_THREAD_ID> [--connection-id <codex-connection-id>] --json
从 Codex 原生会话新建任务成功后，默认用上述动作关联当前会话，无需再询问。用户明确不关联时遵从；接续已有任务时不因普通读取自动新增关系。必须由承载用户请求的会话直接采集具体身份，不委派子智能体（Subagent）代取，不使用共享 CODEX_SESSION_ID、模型上下文协议（MCP）工具服务环境或从其他执行继承的编号。子执行只交还创建结果，由原生会话完成默认关联；普通命令、持续集成（CI）或 DSH 不自动建立 Codex 关系。
关联动作只保存任务与会话的多对多关系，不发送消息、不启动任务或新会话。唯一有效 Codex 接入可自动选择；多个有效接入时明确指定，不能借默认生成智能体猜测。缺少准确身份或有效接入、接入范围变化、关联失败或结果不明时，保留已创建任务并如实说明尚未关联；结果不明先查询已有关系，不重复创建任务、重装插件或重启桌面。成功后核对返回的工作空间、任务与 nativeSessionId，并在回复中使用返回的固定任务链接，供用户在已有侧边页面打开任务。
DSH 原生会话与任务关联
用户在 DSH 原生会话（Session）中要求关联任务（Task），或当前会话（Session）新建任务（Task）成功后，直接核对目标工作空间（Workspace）和任务（Task），由承载用户请求的会话（Session）通过本次原生 Bash 工具（Tool）读取 DSH_SESSION_ID，再显式关联。新任务（Task）默认关联，无需重复询问；用户明确不关联时遵从，接续已有任务（Task）不因普通读取自动新增关系。
buildr dsh link --target <canonical-workspace> --task <task-id> --native-session-id <direct-DSH_SESSION_ID> [--connection-id <dsh-connection-id>] --json
buildr dsh sessions --target <canonical-workspace> [--task <task-id>] [--native-session-id <id>] --json
buildr dsh open-task <task-id> --target <canonical-workspace> --native-session-id <direct-DSH_SESSION_ID> [--connection-id <dsh-connection-id>] --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.
- yesterday Changed ab573c724ea3
- 9d ago Changed · +75 lines · +14 tokens per session 62ac04e21701
- 25d ago Changed · +4 lines 2c1b56b55fb7
- 1mo ago Changed · +19 lines · -11 tokens per session 260b3a4341f4
- 1mo ago Changed · +2 lines ae2a343fab9e
- 1mo ago Changed · +20 lines · -30 tokens per session 337add109953
- 1mo ago First seen · 56 lines · 87 tokens per session scan A f08eb1dc941d
task-manager is a skill published in the GitHub repository BuildrAI/Buildr (28 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 5,929 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…