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 pandazki/pneuma-skills --skill pneuma-preferencesgit clone --depth 1 https://github.com/pandazki/pneuma-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/pandazki/pneuma-skills/pneuma-preferences)<a href="https://agentmods.dev/skills/pandazki/pneuma-skills/pneuma-preferences"><img src="https://agentmods.dev/badge/skills/pandazki/pneuma-skills/pneuma-preferences/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/pandazki/pneuma-skills/pneuma-preferences"><img src="https://agentmods.dev/badge/skills/pandazki/pneuma-skills/pneuma-preferences.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 | $0.00100 | $0.01730 |
| Opus 5.5 | $0.00040 | $0.00692 |
| Sonnet 5.5 | $0.00020 | $0.00346 |
| Haiku 4.5 | $0.00010 | $0.00173 |
Grade A, and why
pneuma-preferences 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Preferences
You have persistent memory about this user stored in ~/.pneuma/preferences/. This is your external memory — it survives across sessions, across workspaces, across modes.
Why This Matters
Every session starts from zero. Without preferences, you guess at style choices, repeat mistakes the user already corrected, and miss patterns you've seen before. Preferences solve this:
- The user corrected you three sessions ago about font sizes → that's recorded, you won't repeat it
- The user always chooses muted colors → you start there instead of guessing
- The user prefers Chinese when writing content → you know before they have to say it again
Preferences are not instructions. They're your understanding of who this user is and how they work. The better your understanding, the less friction in collaboration.
Files
| File | What goes in it |
|---|---|
~/.pneuma/preferences/profile.md |
Cross-mode: aesthetics, language, collaboration style, cognitive patterns, deep profile |
~/.pneuma/preferences/mode-{name}.md |
Mode-specific: slide layout habits, doc formatting style, color choices, etc. |
Files are created by you as needed. An absent file means no profile exists yet — not an error.
Project sessions carry a parallel set of preference files at <projectRoot>/.pneuma/preferences/ — same schema, but scoped to one project. Those belong to the pneuma-project skill, not this one. When a project preference contradicts a personal one, follow the project's and tell the user once with a brief reason — the full conflict policy lives in pneuma-project (read it if you're in a project and the situation comes up).
Three-Layer Model
Preferences organize into three layers, each requiring different levels of evidence:
Layer 1 — Observable preferences (profile.md): Surface patterns you can see directly. Language, aesthetic tendencies, collaboration style, cognitive approach. A few sessions of observation is enough.
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.
- 1mo ago Changed a46813dc11be
- 1mo ago First seen · 125 lines · 100 tokens per session scan A 796c454f3ab2
pneuma-preferences is a skill published in the GitHub repository pandazki/pneuma-skills (161 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 1,730 once invoked, about $0.0004 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
frontend-design
Visual design and aesthetic direction for frontend interfaces. Use when building web pages, landing pages, dashboards, Next.js server components, or applications where visual identity matters. For React patterns and testing, use react-frontend.
frontend-experience
Use this capability for UI architecture, frontend performance, accessibility, routing guards, forms, client state, design-system integration, browser security boundaries, and user-facing AI interfaces. Trigger on React, Vue, Angular, Svelte, components, UI, a11y, WCAG, Core Web Vitals, forms, routing, lazy loading…
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…