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 Supa-Media/context --skill how-we-define-chaosgit clone --depth 1 https://github.com/Supa-Media/contextWrote 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/supa-media/context/how-we-define-chaos)<a href="https://agentmods.dev/skills/supa-media/context/how-we-define-chaos"><img src="https://agentmods.dev/badge/skills/supa-media/context/how-we-define-chaos/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/supa-media/context/how-we-define-chaos"><img src="https://agentmods.dev/badge/skills/supa-media/context/how-we-define-chaos.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 | $0.00065 | $0.01345 |
| Opus 5.5 | $0.00026 | $0.00538 |
| Sonnet 5.5 | $0.00013 | $0.00269 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
how-we-define-chaos 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How we define chaos
Every Context workspace has a chaos score from 0 to 100. Lower is calmer.
orient shows it under "Chaos score" with the folders that would calm it
most, and every write save and manage move or archive answer ends with the
score before and after:
chaos: 34 → 31 of 100 (calmer; lower is calmer)
1-projects/launch: 14 → 9 items (fine)
Nobody tidies for the person automatically. They do it, or they ask you to. This skill is the rubric, so you can tell a change that helps from one that only moves the mess around.
The rubric
A folder's items are the notes and subfolders directly in it. Its about
note (about.md, overview.md, index.md or README.md) describes the
folder and is not an item. Pictures, attachments and dot files are not items
either.
| Items in a folder | Chaos | What it means |
|---|---|---|
| only its about note | 60 | an empty shell: fill it or fold it into its parent |
| 1 | 40 | move the one note out, to the parent or a sibling |
| 2 | 20 | probably one note, or one of a larger folder |
| 3 | 5 | nearly fine |
| 4 or 5 | 0 | calm |
| 6 to 10 | 5 to 25 | fine; 10 is the average mark |
| 11 to 20 | 29 to 65 | crowded: split by theme into subfolders |
| 35 or more | 100 | chaotic |
- Runs count as one. Notes that are one sequence count as one item:
dated notes (
2026-10-01 standup.md), a name with a number (Kings 1toKings 30), or chapters numbered 1 to N with no gaps or repeats. A run needs at least three, and counts one item per 30 notes, so a month of daily notes is fine and a year of them is twelve items. Past 30, group them by month or quarter. Folders named by single letters (an A to Z index, with a catch-all likeother) are a run too. - Long notes. A note past 1,000 lines adds chaos: 10 more per 100 lines,
full chaos at 2,000. A line over 120 characters counts once per 120, so a
wall of text cannot dodge it. Split a long note by section into a folder of
notes with an about note. Meetings (
type: meeting) and notes markedgenerated: trueare exempt. - The workspace is the average over every note, each carrying its folder's chaos (or its own length chaos when that is higher). So a folder weighs what it holds: a crowded folder of 80 notes matters far more than a thin folder of 2.
- Never thin: the root and the built-in folders (Inbox, Projects, Areas, Resources, Clients, Teams, Products). They only count as crowded.
- Never scored: Archive, and everything under it.
- Contacts are scored on hygiene, not count. In
0-inbox/contacts/a page filed under its letter is calm however many there are. A page underother/(no name yet) is half chaos: find the person's name. A page loose in contacts or in a non-letter folder is unsorted. A page whose frontmatterreview:holds a question (a possible duplicate) is chaos until the owner answers it: never clear one yourself. - The inbox counts. A full inbox raises the score on purpose. It is the reminder that it needs sorting.
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 Changed 23b36c857f81
- 7d ago Changed · +7 lines d5cd75b43041
- 9d ago First seen · 92 lines · 65 tokens per session scan A 6e173770bf84
how-we-define-chaos is a skill published in the GitHub repository Supa-Media/context (3 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,345 once invoked, about $0.0003 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 2026-10-11.
Other skills, from other repositories
obsidian-setup-consultant
Use this skill whenever the user wants to install, configure, migrate, design, or connect Obsidian as a second brain, knowledge base, cloud-synced vault, or AI/Hermes-readable memory. It is especially important when the user asks for an Obsidian setup prompt, vault architecture, folder structure, plugin…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
wiki-switch
List, create, or switch named Obsidian wiki vault profiles under the global config directory. Use when changing the active vault, checking which vault is active, or managing multi-vault profiles.
knowledge-base-management
A lifecycle system for managing an Obsidian knowledge base, which is a folder of linked notes. It organizes raw material, AI-maintained wiki pages, and generated views into separate layers.
daily-update
Run or configure the daily wiki maintenance cycle: check source freshness, refresh the index and hot.md, and manage its scheduled 9 AM launchd/systemd/cron reminder. Use for daily or morning wiki refresh or scheduler setup and verification.
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).