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-retrospectivenpx skills add BuildrAI/Buildr --skill task-retrospectivegit 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-retrospective)<a href="https://agentmods.dev/skills/buildrai/buildr/task-retrospective"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/task-retrospective.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 5.1 | $0.00086 | $0.02942 |
| Opus 5 | $0.00043 | $0.01471 |
| Sonnet 5 | $0.00017 | $0.00588 |
| Haiku 4.5 | $0.00009 | $0.00294 |
Grade A, and why
task-retrospective 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 6d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Retrospective
本 Skill 是 buildr.task-retrospective/v2 的默认 provider。Agent负责复盘、当前事实重评与后续承接;Retrospective Application只负责terminal校验与SQLite current Result/处置状态,Task来源关系只通过selected buildr.task-record/v2 provider维护。
1. 恢复任务事实
确认 canonical Workspace 和正式 Task ID,读取 Task Record;Task 必须是 completed 或 abandoned。使用当前Workspace matching retained Buildr controller invocation执行bundled inspect;不得使用candidate cliInvocation、resource payload root或checkout内部driver:
<controller-command> <controller-args-prefix...> __internal task-retrospective inspect --task <task-id> --target <canonical-workspace>
已有Result可以重做并完整替换;没有Result只是“尚未复盘”。同时读取 disposition 与 currentDigest;不要打开SQLite;不读取、迁移或删除.buildr/asset-review/。
在复盘生成前建立一次有界执行事实图,只读取当前runtime可达且与效率、重复、等待、失败恢复或人机协作直接相关的最小事实:Task Record时点与终态、适用的Development/Review/Verification current摘要、相关Execution Record/Finish timing、当前session工具结果,以及已有current reportMarkdown。已有复盘是本次重新思考的证据之一,不是必须保留的结论。没有某类事实时标记缺口,不为补齐图谱遍历全部owner、读取完整日志或增加任务消耗;同一事实已在当前上下文可用时不重复回读。该图只存在于Agent任务上下文,不写入Result之外的store、Receipt、history或分析平台。
2. 生成一份自由复盘
只基于当前session/runtime可访问的任务步骤、工具结果和最终事实,重点寻找:
- 哪些步骤耗时最多或token消耗最大;
- 哪些推理、检索、尝试、验证或恢复发生重复;
- 哪些等待、阻塞或环境准备可以前移、缓存或确定化;
- 哪些选择应更早交给人,哪些可以由workflow/harness直接确定;
- 哪些Buildr引导本身增加了不必要工作量。
报告使用自由Markdown,不要求固定标题、评分、分类或结构化建议。Token 数据按证据可见性处理:可信可得时记录数值、来源和覆盖范围;部分可得时明确覆盖的步骤、阶段或调用及其不代表完整 Task;不可得时直接标记缺失,并继续使用耗时、重复尝试、等待、工具调用和人机协作等可观察事实。不得为了补齐 Token 数字回放完整上下文、读取隐藏推理、强制估算、新增采集流程或增加任务消耗;其他精确成本数据不可见时同样写明缺口并区分观察事实与推断。不得声称读取隐藏推理、完整对话、完整工具日志或后台事件。
用户或团队给出的同类任务耗时参考区间,只作为当前任务复杂度下的比较、解释和优化背景;报告应说明适用范围及偏离原因,不把它固化为通用产品阈值、Result字段、gate、pass/fail标准或自动缩减验证范围的依据。
确定性流程候选
每次生成或重做复盘都主动判断是否存在确定性流程候选,但报告仍是自由Markdown,不要求固定标题、候选数组或评分。可信候选必须有重复证据,或单次已经造成高成本/高风险,并同时说明:
- closed输入、唯一Owner、明确停止条件、可验证结果与幂等/有界恢复;
- 哪些机械步骤可由Application、CLI workflow、checker或test确定化;
- 哪些目标、业务判断、风险取舍和授权仍由人和Agent保留;
- 预期节省、失败风险、证据局限与建议资产落点。
候选必须通过Core哲学过滤:Buildr应该约束Agent不要做错事,而不是要求Agent必须通过Buildr才能做事。 要求普通动作必须经过Buildr、把推荐路径变成唯一合法路径、建立通用许可层/生命周期gate、自动替代专业判断或自动修改Rule/Skill/workflow的方向,不得作为可固化候选;说明违反的authority/判断边界后保留Agent在现有授权与安全边界内直接执行的路径。证据不足、仍依赖业务语义、边界无法闭合或收益不足时,如实保留为普通优化方向或说明没有可信候选,不为填充报告虚构候选。
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.
- 6d ago First seen · 120 lines · 86 tokens per session scan A ab9d550d334e
task-retrospective is a skill published in the GitHub repository BuildrAI/Buildr (24 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 2,942 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.
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…
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…
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…