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/laurigates/dotfiles/shareablenpx skills add laurigates/dotfiles --skill shareablegit clone --depth 1 https://github.com/laurigates/dotfilesWhat 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 | $0.00120 | $0.01407 |
| Opus 5 | $0.00060 | $0.00704 |
| Sonnet 5 | $0.00024 | $0.00281 |
| Haiku 4.5 | $0.00012 | $0.00141 |
Grade C, and why
shareable scanned grade C with 1 finding 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 2d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
```text <layman message> ``` ### [ ] technical ```text <technical message> ``` ### [ ] one-liner ```text <one-sentence hook> ``` ### [ ] takeaway ```text <try-this tip> ``` --- ``` Author the `text` bodies in **l How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shareable — bite-sized sharing for Google Chat
A low-friction workflow for sharing experiences, successes, and useful failures with colleagues on Google Chat. The user has two spaces in mind — an AI-use-case space ("tekoäly työkaverina", includes non-technical colleagues) and a technical space — but drafts are organized by register, not by space. The user routes each register to whichever space fits when they paste.
Delivery is draft → clipboard → the user pastes. Posts as the user (not a bot), no credentials, human-in-the-loop. No webhook, no deploy.
The four registers
Every topic is drafted in up to four registers. Default to producing all four; honor a request for a subset ("just the layman one", "make the takeaway").
| Register | What it is | Shape |
|---|---|---|
| layman | Lead with the human outcome. Zero unexplained jargon — a non-technical colleague must get it. | 3–6 short lines, one idea |
| technical | The mechanism, the how. Tool names fine. | Same brevity, mechanism-first |
| one-liner | A single scannable sentence — a hook. | One sentence (use prose-distill) |
| takeaway | Framed so a colleague can adopt it themselves. | "Try this: …" |
Categories (set per topic in the note's metadata): experience |
success | useful-failure. Support useful-failure explicitly across all
registers — "I tried X, it didn't work, here's what I learned" is as shareable
as a win. The user asked for failures, not just successes.
Quality bar
Cold-read topic, two registers, to calibrate tone:
layman — 💡 A small habit that's quietly improved everything I send "outward" (bug reports, docs, messages): before it goes out, I have a separate, fresh AI read it with zero background — like handing it to a brand-new colleague. If it confuses them, it'll confuse real readers too. Catches the "obvious-to-me, baffling-to-everyone-else" trap before it ships.
one-liner — I let a second, context-free AI "cold read" anything I send outward — if a fresh reader is confused, so will real ones be.
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.
- 2d ago First seen · 132 lines · 120 tokens per session scan C 750d200e3d39
shareable is a skill published in the GitHub repository laurigates/dotfiles (10 stars, last pushed 3d ago), licensed MIT. It adds 120 tokens to every session and 1,407 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-oss-skill
Create well-formed Agent Skills following the agentskills.io specification. Scaffold directories, write SKILL.md files, bundle scripts, and structure instructions for progressive disclosure. Use when creating a new skill, reviewing skill structure, optimizing a skill description, or setting up evals for skill quality.
course-development
Design executable technical curricula, lessons, and labs with prerequisites, guided practice, accessibility, platform checks, and course release acceptance.
diataxis
Audit, write, or revise docs under docs/ (or repo equivalent) when the artifact is a tutorial, how-to, reference, or explanation — anything not already a README, CONTRIBUTING, ADR, or CHANGELOG. Forces a Diátaxis mode pick before writing, then loads mode-specific anti-patterns. Use when creating or editing a…
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
share-learning
Promote a team-relevant learning to the shared team-knowledge repo, deduping against existing notes first. Triggers "share this", "promote to the team repo", "add to the knowledge base", or after a gotcha/decision/convention worth team-wide awareness.