Borrowing it
Nothing to install: this file belongs to binary16labs/prime-silo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/binary16labs/prime-silo/main/.claude/skills/prime-silo-experience/SKILL.mdgit clone --depth 1 https://github.com/binary16labs/prime-siloWrote 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/binary16labs/prime-silo/prime-silo-experience)<a href="https://agentmods.dev/skills/binary16labs/prime-silo/prime-silo-experience"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/prime-silo-experience.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 5.1 | $0.00094 | $0.01687 |
| Opus 5 | $0.00047 | $0.00843 |
| Sonnet 5 | $0.00019 | $0.00337 |
| Haiku 4.5 | $0.00009 | $0.00169 |
Grade A, and why
prime-silo-experience 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 8d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Prime-Silo experience — identity, discovery, motion
The product is Prime-Silo. The guide who lives inside it is Agent Benny (the german
shepherd). "Space Agent" is a dead upstream name — it must never appear on a user-facing surface
(strings, titles, alt text, logos, docs prose). Identifiers (space-desktop: IPC, node space
CLI, file names, package names) are protected until Workstream H — do not rename them.
The feeling to build: walking into a quiet, beautifully organized grain silo with a very good dog showing you around. Calm by default; kinetic at the exact moments that deserve it. The marketing site (website/) already nails this — the app must feel like the same product.
1. One palette, two surfaces
All app color resolves through var(--*) tokens in
app/L0/_all/mod/_core/framework/css/colors.css (enforced by scripts/gates/c0.mjs — hex
literals outside colors.css fail the commit). The family: alabaster/cream grounds, moss/charcoal
greens for depth, rust for the ONE primary action, sage/taupe for structure. Depth = the three
--elevation-1/2/3 tokens only. Spacing/radius/measure from layout.css, type from type.css
(base ≥16px, line-height 1.5, ≤70ch, never justify). Read architecture/DESIGN-SYSTEM.md in
full before any CSS — it is short and it is law.
2. Progressive discovery (the ADHD contract, C0)
- One decision per screen. First-run, wizards, and setup flows present exactly one choice, then advance. Never a settings wall.
- One primary action per view, rust-accented, visually dominant. Everything secondary sits
behind a consistent
More ▸disclosure. - Teach by doing. Empty states offer the first action, not documentation ("Drop a PDF to begin"). After the first success, suggest exactly 3 next actions.
- Long work is honest work: always
Step n of m+ one plain line of "what happens next." Progress lands as a card, never a modal wait. - Benny narrates transitions in first person, short and warm: "I'll keep your documents on this machine." — never marketing voice inside the product.
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.
- 8d ago First seen · 108 lines · 94 tokens per session scan A 29c5d0f61d21
prime-silo-experience is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 1,687 once invoked, about $0.0005 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
kernel-chat-web-design
Guides the design, layout, styling, and interactivity of kernel.chat editorial spreads and standalone artifact editions. Use this skill when editing or creating pages, React components, CSS files, or single-file HTML artifacts in the kernel.chat project to enforce the POPEYE-inspired bilingual design grammar and the…
kernel-chat-design-qa
Audits kernel.chat pages for responsive visual craft, accessibility, motion safety, interaction truth, runtime health, and production rendering. Use when reviewing an issue or artifact, checking whether a design is finished, comparing desktop and mobile, validating reduced motion or print, finding overflow and broken…
kernel-chat-art-direction
Creates distinctive editorial art direction for kernel.chat issues before implementation. Use when choosing an issue's visual concept, typography, composition, cover system, media grammar, responsive transformation, or motion intent; when a page feels generic or lacks character; or when original image and video assets…
kernel-chat-design
Use this skill to generate well-branded editorial interfaces and assets for kernel.chat ("Magazine for City Coders" — an independent magazine that is an unnamed homage to POPEYE), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and editorial…
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
animation-vocabulary
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and…