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/midnightdarling/collate/constellationpx skills add MidnightDarling/collate --skill constellatiogit clone --depth 1 https://github.com/MidnightDarling/collateWrote 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/midnightdarling/collate/constellatio)<a href="https://agentmods.dev/skills/midnightdarling/collate/constellatio"><img src="https://agentmods.dev/badge/skills/midnightdarling/collate/constellatio.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 | $0.00045 | $0.01200 |
| Opus 5 | $0.00023 | $0.00600 |
| Sonnet 5 | $0.00009 | $0.00240 |
| Haiku 4.5 | $0.00005 | $0.00120 |
Grade A, and why
constellatio 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 3d 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.
What it actually says
constellatio
这个 skill 做什么
输入一个在历史上被反复征用、各代读法互相矛盾的现象(李鸿章、王安石变法、 鸦片战争、五四),输出两样东西:
- 一份接受史分析 — 每个时代怎么读的、为什么这么读、变迁追踪的是读者 还是对象
- 一个判断 — 对象内部的什么结构让所有时代的投射都能贴住(屏幕属性)
第二点是这个 skill 在普通接受史之上唯一多做的事。普通接受史告诉你"各代 怎么读了";这个 skill 多问一句:"对象身上什么东西让它能被这样反复读而不 耗尽?"
可选地,分析可以搭配一张暗夜星图 viewer — 同一组事件固定不动,各代的连 法在上面各画一层,让眼睛直接比较散文需要绕着弯说的东西。
输入
Target: $ARGUMENTS
- 一个现象名(
李鸿章、五四、鸦片战争)→ 从公开材料做 - 一个 workspace 目录 → 读
<ws>/final.md,当作待诊断的读法之一 - 一个
.md文件 → 同上 - 空 → 问用户哪个现象,以及已经知道哪些互相矛盾的读法
至少三种互相矛盾的读法才值得动这个 skill。不到三种,普通的论证分析就够 了。超过七种,通常是在凑数。
方法
三步。前两步是标准接受史工作,第三步才是这个 skill 的独有贡献。
第一步 · 底图。 列出这个现象里不可压缩的事实 — 无论谁来读都必须处理 的事件、人物、文本。不解读,只列。
第二步 · 每代读法当作诊断。 每一个时代的读法,问的不是"读得对不对", 是"这个时代需要从历史里取走什么来支撑自己的当下"。亮了什么、压暗了什 么、不愿看什么 — 这些是诊断材料。同时追踪:各代读法的变化到底在追踪什 么?几乎从来不是关于对象本身的新发现,通常是读者群体自己的合法性危机在 变。
第三步 · 屏幕属性。 这是这个 skill 唯一真正多做的事。问:对象内部的 什么结构让每一代的投射都能贴住?通常是一个真实存在于对象内部的矛盾(启 蒙 + 救亡同时在场;开明改革 + 帝国困局同时在场)— 不是后人构造的复杂 性,是对象本身的双重结构。找到这个,才能解释为什么这个现象被反复征用而 不耗尽。找不到,就诚实说找不到。
输出
- workspace 模式 →
<workspace>/analysis/{stem}_constellatio.md - 单文件模式 →
analysis/{stem}_constellatio.md - 纯现象模式 → 问用户放哪
散文六段:
- 现象 — 名称,不装饰
- 不可压缩面 — 每个读法都必须包括的事实
- 每代读法的诊断 — 每个时代需要这个现象是什么,以及为什么
- 变迁追踪的是什么 — 跨时代变化到底在追踪什么
- 屏幕属性 — 对象内部让投射贴住的结构
- 当下读法的诚实 — 当代的综合本身也是一种时代读法,不是终审
可选 · 暗夜星图 viewer
当各代读法可以在同一组事件上做明暗对比时,一张星图可以让眼睛直接做散文 需要绕着弯说的比较。
星图不是分析。它把各代的连法摆在视觉上,让读者自己看。诊断、屏幕属性、 变迁追踪 — 这些只在散文里。
做 viewer 时参考 references/viewer-spec.md(美学 + 技术规范)和
references/example-may-fourth.html(canonical 例子)。散文例子见
references/example-may-fourth.md。
诚实
- 只有两种读法且只是互相矛盾 → 不值得用这个 skill
- 屏幕属性找不到 → 说找不到,不要发明一个对象里不存在的矛盾
- 没有人提出过的读法不是读法,不要为了凑数而发明立场
- "无法归结"有时候就是诚实的结论
- 当代的综合和过去各代一样,是时代读法,不是终审 — 说清楚这件事
What ships with it
3 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.
- 3d ago First seen · 91 lines · 45 tokens per session scan A 338bb0819328
constellatio is a skill published in the GitHub repository MidnightDarling/collate (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,200 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
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
honey-px
Read huge read-only text as PNG pages; big input cut.
honey-debt
Harvest honey shortcut markers into a debt ledger.
honey-memory
Per-project persistent memory files indexed in MEMORY.md.
review-diff
Scan git diffs for project-specific anti-patterns. Triggers on: 'scan diff', 'check diff', 'anti-pattern check', 'pattern scan', 'review changes'.
orchestrate
Drive a plan to completion by orchestrating implementer, reviewer, and critic agents across waves of parallel work. Use when the user says "orchestrate", "implement this plan", "execute plan", "drive this", or approves a plan for execution.