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 Caravaca-Labs/puzzletide-cli --skill puzzletide-crosswordgit clone --depth 1 https://github.com/Caravaca-Labs/puzzletide-cliWrote 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/caravaca-labs/puzzletide-cli/puzzletide-crossword)<a href="https://agentmods.dev/skills/caravaca-labs/puzzletide-cli/puzzletide-crossword"><img src="https://agentmods.dev/badge/skills/caravaca-labs/puzzletide-cli/puzzletide-crossword.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 | $0.00058 | $0.00787 |
| Opus 5 | $0.00029 | $0.00394 |
| Sonnet 5 | $0.00012 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
puzzletide-crossword 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 7d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PuzzleTide Crossword
Generate crossword puzzles with the local PuzzleTide CLI.
Never hand-draw a crossword grid. Language models cannot reliably keep intersecting words consistent. The CLI places words with real intersections, assigns standard crossword numbering, and validates that every clue's answer matches the grid before returning — words that cannot interlock are reported as unplaced instead of silently broken.
Prefer the local CLI. Check availability in this order:
ptide --version
puzzletide --version
npx puzzletide --version
If none of those work, ask the user before installing (npm install -g puzzletide).
Generate with your own clues (best quality)
Write the clues yourself — you are good at clues; the CLI is good at grids:
ptide crossword generate --words "PARIS: Capital of France; TOKYO: Capital of Japan; OSLO: Capital of Norway"
For longer lists use a JSON file:
ptide crossword generate --file words.json --pdf crossword.pdf
# words.json: [{"word": "PARIS", "clue": "Capital of France"}, ...]
Generate from a themed word bank
Clues are auto-generated puzzle-style hints (unscramble, letter counts):
ptide crossword generate --theme food/fruits --count 10
For better clues, pull the words and write clues yourself:
ptide words list food/fruits --count 10 --json
# ...then pass your own word:clue pairs to crossword generate.
Printable and structured output
ptide crossword generate --file words.json --pdf crossword.pdf --title "Science Review"
ptide run puzzle.crossword.generate --theme animals --json
The PDF has three sections: empty numbered grid, clue list, and solution.
--json returns the grid ("#" = black cell) plus across/down clues with
coordinates — ready for rendering in an app.
Links
- Play online: PuzzleTide crossword
- Worksheets: printable puzzles at puzzletide.com
- Source and docs: GitHub · npm · CLI reference
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.
- 7d ago First seen · 93 lines · 58 tokens per session scan A e56e0ba0bece
puzzletide-crossword is a skill published in the GitHub repository Caravaca-Labs/puzzletide-cli (0 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 787 once invoked, about $0.0003 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
sprite-animation
A pixel / sprite-style animated explainer slide — full-bleed cream stage, bold display year, animated pixel-art mascot (e.g. Hanafuda card, mushroom, or 8-bit console), kinetic Japanese display type, ticking timeline ribbon. Reads like a single frame of an educational motion video — looping CSS keyframes, no JS, ready…
html-ppt-course-module
Online-course / workshop module deck — warm paper background + Playfair serif, persistent left sidebar of learning objectives, MCQ self-check page. Use for teaching modules, training materials, workshop slides.
baoyu-comic
A tool for creating educational comics from supplied text, files, links, or topics. It can cover explanations, biographies, and tutorials in different visual styles, tones, layouts, sizes, and languages.
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.
html-ppt-zhangzara-daisy-days
A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team.
get-rep-call-feedback
Use when the user wants evidence-backed coaching for one rep's calls, especially by comparing the rep with peer examples to identify repeatable best practices, specific upgrade moments, and practical next-call language.