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 hxy91819/mason-skills --skill large-task-planninggit clone --depth 1 https://github.com/hxy91819/mason-skillsWrote 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/hxy91819/mason-skills/large-task-planning)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/large-task-planning"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/large-task-planning/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/hxy91819/mason-skills/large-task-planning"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/large-task-planning.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.02074 |
| Opus 5 | $0.00016 | $0.01037 |
| Sonnet 5 | $0.00006 | $0.00415 |
| Haiku 4.5 | $0.00003 | $0.00207 |
Grade A, and why
large-task-planning 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Large Task Planning
这是流程类 Skill,仅在用户显式调用 $large-task-planning 时运行。
为两种受众生成一个计划系统:人通过 SPEC.md 理解目标和取舍,通过 STATUS.md 判断是否顺利、是否
需要介入;Agent 通过结构化 JSON 领取、执行和恢复。JSON 是唯一事实源,两份 Markdown 都由脚本按
人的阅读问题重新组织,不逐字段转抄 Agent 细节。
创建或检查计划前读格式契约。发现 v1 的 epics/ + stories/ + agent/*.json + 项目进展.md 时,再读迁移说明。维护与 orchestrator 共享的
职责、完成语义或回溯 Matt 上游借鉴时,读联合核心设计。
产物与受众
<topic>/
├── SPEC.md # 人:为什么做、完成后怎样、承诺、边界、取舍与验收
├── STATUS.md # 人:已得到什么、正在验证什么、下一步与介入点
└── agent/
├── plan.json # Agent:稳定 Goal、规格、黄金案例与 final Story
└── stories/*.json # Agent:执行单元、状态、依赖、上下文与 handoff
人读文档不按 Epic/Story 模板展开,也不展示内部 ID、依赖图、代码锚点、write scope、owner、attempt
或原始命令日志。Agent JSON 不承担项目介绍文的可读性。相同事实只在 JSON 维护一次;render 根据
人的阅读任务重新组织信息。
SPEC.md 面向首次加入项目或需要做取舍的人,按“为什么要做 → 完成后是什么样 → 对使用者的承诺 →
必须守住的边界 → 已定取舍 → 怎样确认完成 → 交付路线”阅读。STATUS.md 面向正在跟进项目的人,先给
当前判断,再给正在推进、接下来、之后路线、需要关注和已经得到的结果。若一项 Agent 字段不能帮助人
理解终态、判断进展或采取行动,就不应出现在 Markdown 中。
先清除决策迷雾
只有任务明显超过一个 fresh context,或需要跨会话、跨 Agent 恢复时才使用本 Skill。单会话可安全 闭环的任务直接执行。
先区分:
- 决策迷雾:产品结果、正确答案或边界尚不能清楚描述。先调查、原型或询问。
- 执行路径:结果和判据已明确,只需选择可逆实现。由 Agent 决定并继续。
只有会改变用户所得、公开契约、兼容/迁移、安全、发布物、运维责任或显著成本的选择属于用户决策。 已有对话和仓库事实足够时直接综合;不能安全推断时,只问能解除阻塞的最小问题。不要把仍在迷雾中的 工作预切成虚构 Story。
编译规格
- 读取适用的
AGENTS.md、需求、规格、ADR、领域词汇和代码入口;检查 branch、git status --short、git worktree list与基线。区分事实、假设、边界和范围外事项。 - 在
plan.json.spec中写 Problem Statement、用户视角的 Solution、完整但不重复的 User Stories、 Boundaries、重大 Decisions、公共 Testing seams 和 Out of Scope。这一结构借鉴 To Spec,但不绑定其 tracker 或安装包。 - 写黄金案例。每个
GC-NN都有可复现 fixture、连续 actions、独立 oracle 和要保留的 evidence。 没有已知正确结果的演示不是黄金案例。 - 选择最高且稳定的公开测试 seam。优先沿用仓库已有 seam;测试可观察行为,不绑定实现细节。
编译执行路径
把工作拆成 tracer-bullet Story:每张 Story 交付一条窄而完整、可独立验证的纵向结果,并能由一个
fresh、便宜的 Worker context 完成。粒度判据是 economy 或 standard 档模型能独立做完;预计需要 strong
才能完成的 Story 先拆,而不是留给 orchestrator 升档。优先把 Acceptance 写成可由脚本或测试直接判定
的形式,这类 Story 在执行时可以跳过独立 Validator。依赖字段 blocked_by 只表达真正阻止开工的边。
What ships with it
5 files 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 · +15 lines 978ab209247c
- 7d ago Changed · -156 lines · +6 tokens per session b58a0a0ce425
- 11d ago First seen · 277 lines · 26 tokens per session scan A fdb4bab46880
large-task-planning is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 2,074 once invoked, about $0.0002 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 2026-08-31.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…