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 miniidealab/openlogos --skill slice-plannergit clone --depth 1 https://github.com/miniidealab/openlogosWrote 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/miniidealab/openlogos/slice-planner)<a href="https://agentmods.dev/skills/miniidealab/openlogos/slice-planner"><img src="https://agentmods.dev/badge/skills/miniidealab/openlogos/slice-planner/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/miniidealab/openlogos/slice-planner"><img src="https://agentmods.dev/badge/skills/miniidealab/openlogos/slice-planner.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 | $0.00013 | $0.04079 |
| Opus 5.5 | $0.00005 | $0.01632 |
| Sonnet 5.5 | $0.00003 | $0.00816 |
| Haiku 4.5 | $0.00001 | $0.00408 |
Grade A, and why
slice-planner 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 1mo 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Slice Planner（切片规划）
在变更 merge 之后、implement 之前，把已合并规格拆成"良构
[code]切片"，写入tasks.md的[code]section。 这是 launched 变更下[code]切片的唯一事实源——切几片、每片做什么，只在此处用六维打分 + 删后续证伪门决定一次；下游code-implementor只逐行消费，不再重复打分、不再自行分批。
触发条件
openlogos next落在ready-to-implement驻留态 /plan-slices节点（宿主 driver 注入"规划切片"上下文）- 用户在变更 merge 完成后说"划分切片"、"写
[code]"、"规划实现任务"
前置依赖（强制，缺一不可）
- 活跃提案存在且已完成 spec-complete：提案目录有
SPEC_MERGED（或MERGED）marker。- 含
[delta]提案：该 marker 表示 delta 已真实合入主规格。 - 无
[delta]的纯代码提案：该 marker 必须由 no-deltaopenlogos merge <slug>写入，表示本次没有规格 delta 但规格阶段已完成。
- 含
- 规格 delta 已合并进主文档，或 no-delta
SPEC_MERGED明确记录本次无需文档 delta。 - 测试用例已合并、ID 已定：相关
logos/resources/test/*-test-cases.md或显式复用声明含真实UT-Sxx-../ST-Sxx-../SMOKE-*ID。
若以上任一不满足（尤其缺
SPEC_MERGED或测试 ID 未定），说明尚未到切片时机。禁止用占位 ID 切片，提示先完成 no-delta merge / merge 或补齐真实测试 ID。这正是本环节挪到 spec-complete 后的根本原因：对已定稿规格 + 真实测试 ID切，而非对草案或隐含假设猜。
核心职责
唯一交付物：tasks.md 的 ## [code] section——一组过了删后续证伪门的良构切片，每条末尾标注其覆盖的真实 UT-Sxx-.. / ST-Sxx-..。
不产 proposal.md、不产 [delta]、不产 [deploy]（那是 change-writer 的职责），不写业务代码（那是 code-implementor 的职责）。
执行步骤
Step 1: 读已合并规格 + 真实测试 ID
读 logos/changes/<slug>/proposal.md 的变更范围，再读已合并进 logos/resources/ 的架构 / 场景 / 功能规格与 test/*-test-cases.md，列出本次要落地的代码能力清单与可用的 UT/ST ID 全集。
Step 2: 六维打分（决定"是否大任务"）
| 维度 | 0 分 | 1 分 | 2 分 |
|---|---|---|---|
| 影响范围 | 1 个文件或局部函数 | 2-5 个相关文件 | 跨模块 / 跨服务 / 跨端 |
| 行为复杂度 | 单一路径 bugfix | 2-3 个分支 | 多场景 / 状态机 / 异步流程 |
| 契约变化 | 无 | CLI/API 输出小改 | API/DB/flow/兼容契约变更 |
| 测试规模 | 1-3 个用例 | 4-8 个用例 | 9+ 个用例或多类测试矩阵 |
| 风险等级 | 易回滚 | 有兼容性风险 | 涉数据、安全、部署、迁移 |
| 不确定性 | 原因明确 | 1 个待验证假设 | 多个未知点 / 需要探索 |
- 0-7 分 = 不是大任务 → 单切片。即使含代码 + 测试 + reporter + golden，也只写 1 条
[code]。 - 8 分及以上 = 大任务 → 进入 Step 3 尝试垂直拆分。
Step 3: 垂直/横向判别器（选对切片轴）
只有按子能力垂直拆分才算合格；禁止按工种 / 层 / 文件横切。给每片起名后看名字落在哪类：
- 🚩 横向红旗（禁止，命中即推倒重切）：片名是层 / 文件 / 工种—— "地基 / 底座 / 读写 / 管道 / 接线 / helper / 工具函数 / config 接入 / schema / 类型 / 数据层（单独）/ UI 展示（单独）/ 写测试 / 补 reporter / 重拍 golden"。 一组切片若读起来像"先建底座 → 再写逻辑 → 再补工具 → 最后接 UI"，就是把施工顺序当成了切片，必须重切。
- ✅ 垂直合格：片名是一条端到端能力线 / 一个场景 / 一个独立子模块的完整闭环——数据→逻辑→产出→该片测试 一并落在同一片内。
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.
- 1mo ago Changed · +4 lines · +13 tokens per session 394258a6ab1f
- 1mo ago First seen · 192 lines · 0 tokens per session scan A 2120206ea38c
slice-planner is a skill published in the GitHub repository miniidealab/openlogos (322 stars, last pushed 4d ago), licensed Apache-2.0. It adds 13 tokens to every session and 4,079 once invoked, about $0.0001 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
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…
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.