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-developmentnpx skills add BuildrAI/Buildr --skill task-developmentgit 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 | $0.00080 | $0.05629 |
| Opus 5 | $0.00040 | $0.02815 |
| Sonnet 5 | $0.00016 | $0.01126 |
| Haiku 4.5 | $0.00008 | $0.00563 |
Grade A, and why
task-development 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 2d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Development
本 Skill 编排buildr.task-development/v2。它通过Buildr内部Task Development Application工作；仍没有公共Development CLI，Buildr Web只消费Application inspect的只读投影来展示通用Development。Parent coordination另有受控公共CLI/Buildr Web surface，但Development Receipt仍只能由Application写入。不得手写Development Receipt。
所有Development内部action必须使用buildr task next返回的environment.controllerInvocation.command + argsPrefix，再追加__internal task-development <action> ...；不得使用Task Environment的candidate cliInvocation、resource payload root或checkout中的src/interfaces/internal路径写canonical Workspace。
阶段化上下文与效率边界
进入或继续已有Formal Task时，先消费buildr task next <task-id> --target <canonical-workspace> --json的compact snapshot。它返回matching Environment execution roots、retained controller、保存的Development applicability和一个typed next；默认不复制完整Receipt。required只覆盖authority/identity恢复，recommended不构成gate，用户选择其他合法动作时仍交给实际owner contract判断。只有诊断恢复、审查或明确请求完整evidence时才读取详细Result。
只在某个专业动作成为 next executable action 时读取该动作的 capability contract、selected provider 与直接 authority：Planning Review、current knowledge、Formal Verification、Completion Review 和 Finish 的完整指引分别在进入对应阶段前装配，不在 proposal 前一次性预读整个生命周期。当前动作仍必须遵守已触发 Skill、required Rule、授权与 result evidence，按需读取不等于跳过门禁。
首次修改 proposal、Skill、代码、测试或当前知识前，复用 triage 建立的一次有界 authority source map；若尚未形成，则从直接相关的 canonical specs、current knowledge、实现、测试与 registries 建立。该 map 保留在 Agent 工作上下文，不写入 Receipt 或其他产品 store；只有 scope、authority 或相关事实变化时才增量刷新。
Task 可能产生用户可见前端 UI 变化、且 triage 尚未询问时，先询问用户是否需要界面原型（UI Prototype）。只有当前任务已有明确确认，才在正式前端实现前加载 selected ui-prototype Skill；用户拒绝、未确认或要求继续时不生成并继续本流程。当前 Task 已生成一个或多个原型且用户未明确要求忽略时，正式前端编辑前必须读取全部相关原型，并按其信息架构、布局和交互开发；需要成为正式行为的选择继续写入 design、delta specs、Brief 与 tasks。UI Prototype 与忽略选择都不保存为 Development node、gate、Result、Receipt 或 blocker。
proposal 启动耗时、重复 Skill/authority 读取、重复命令、实现到 handoff 耗时与 verification wall-clock 只作为 task-retrospective 跟踪、评估和优化的参考。它们不进入专业 Result、Development gate、Task status、Candidate identity或自动 skip/advance 决策，也不构成 pass/fail threshold。
日常 Development transition 或状态回读只需要 current identity、applicability 与下一步方向时，优先使用Task Entry Snapshot；直接调试Development owner时可对内部driver显式使用--compact。两者都只是response projection，不追加观察或写入，并以同源formalVerificationReadiness说明正式验证交接是否尚未到达、存在明确blocker或需要current knowledge即时确认。需要完整Receipt、专业Result引用或handoff snapshot时仍读取默认完整result。typed next与legacy nextActions来自同一判定；它们不执行动作、不代表授权，也不得越过当前阶段才加载的selected provider。
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.
- 2d ago First seen · 144 lines · 80 tokens per session scan A 97e821504a41
task-development is a skill published in the GitHub repository BuildrAI/Buildr (24 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 5,629 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
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
github-workflow
Use GitHub workflow tools to read work status, draft reports, summarize follow-ups, and execute only approved issue mutations.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
codex-session-product-reviewer-maintainer
Use when reviewing a local Codex session, task, thread, or commit as a product manager or first-principles reviewer for product correctness, scope, behavior, validation, and whether the task solved the right user problem.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.