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 shinyobjectz/montology --skill intakegit clone --depth 1 https://github.com/shinyobjectz/montologyWrote 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/shinyobjectz/montology/intake)<a href="https://agentmods.dev/skills/shinyobjectz/montology/intake"><img src="https://agentmods.dev/badge/skills/shinyobjectz/montology/intake/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/shinyobjectz/montology/intake"><img src="https://agentmods.dev/badge/skills/shinyobjectz/montology/intake.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 | $0.00157 | $0.01473 |
| Opus 5.5 | $0.00063 | $0.00589 |
| Sonnet 5.5 | $0.00031 | $0.00295 |
| Haiku 4.5 | $0.00016 | $0.00147 |
Grade A, and why
intake 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The intake: the words come from the people, the gate comes from the db
A fresh monty init leaves an empty ontology. The code has names; the
people have meanings; nobody has written down which is which. The intake
asks — in a form, because a form is a record and a chat is not — and ends
with monty onto add, never with prose. Everything lands in
.monty/answers/.
The loop
monty intake ask <phase.json> # serves the form, BLOCKS until submitted, writes .monty/answers/<phase>.answers.json
monty intake answers # everything answered so far, merged — read this before writing the next phase
monty intake status # what is open, what is answered, whether the glossary is rendered
monty intake glossary --open # the closing page: the whole ontology, rendered from the database
ask blocks until the submit — run it with the Bash tool's
run_in_background and keep working; the process exits the moment the
answers land, which re-invokes you with the result line
answered .monty/answers/<phase>.answers.json (N answers). If you would
rather watch the file than the process, a Monitor on
until [ -f .monty/answers/<phase>.answers.json ]; do sleep 1; done; echo answered
gives the same single notification. Tell the person the form has opened
(the URL is the first line ask prints) and that the next round opens
when it is ready — never poll them in chat for answers the form is
collecting.
Phase 1 — the domain (fixed)
phases/1-domain.json in this skill folder is the opening round; serve it
as-is. It asks what the system is, who it serves, what the central things
are called, which words cause arguments, and what frameworks' words are
spoken at the boundary.
Phase 2 — what the code is asking for (written from phase 1 + the scan)
Run monty scan --candidates 15 (and monty explain if the repo is
unfamiliar). Copy phases/2-candidates.json and REWRITE it: one question
per load-bearing candidate, quoting the count (the code declares "Harness" 14 times — what is it?), with the phase 1 answers shaping the
options. A phase 2 that could have been asked of any repo is one you did
not write. Keep it to 6–10 questions; every question exists because the
scan or a phase 1 answer raised it.
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.
- 1mo ago Changed · +35 tokens per session db3fd48cf7b6
- 1mo ago First seen · 106 lines · 122 tokens per session scan A c1a08f8ab453
intake is a skill published in the GitHub repository shinyobjectz/montology (50 stars, last pushed 6d ago), licensed Apache-2.0. It adds 157 tokens to every session and 1,473 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
extract-design
Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…
omd-apply
A skill that applies a project's DESIGN.md file as visual and brand guidance for interface work. It covers components, colors, fonts, layout, copy, motion, and visual assets.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
bench-fixture-gen
Generates the shared per-task fixture that every competing arm starts from: a realistic dataset plus an image asset base. Fairness rule: fixtures are generated ONCE per task by this preprocessor and sealed (sha256) before any arm runs; arms never generate their own.
design-md-extractor
Extract and document the visual style of public websites as reusable DESIGN.md files. Use when the user asks to analyze a website's design system, extract styles, create design tokens, produce DESIGN.md, generate an agent-readable style guide, or build from a website's visual language.
dembrandt
A TypeScript command-line tool that renders a web page with Playwright and examines its actual styles. It turns colours, typography, spacing, borders, shadows, animation curves, components, and breakpoints into structured design tokens.