Borrowing it
Nothing to install: this file belongs to hs737/mcp-server-for-ynab. 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/hs737/mcp-server-for-ynab/master/.agents/skills/generated-assets/SKILL.mdgit clone --depth 1 https://github.com/hs737/mcp-server-for-ynabWrote 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/hs737/mcp-server-for-ynab/generated-assets)<a href="https://agentmods.dev/skills/hs737/mcp-server-for-ynab/generated-assets"><img src="https://agentmods.dev/badge/skills/hs737/mcp-server-for-ynab/generated-assets.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 | $0.00026 | $0.00957 |
| Opus 5 | $0.00013 | $0.00478 |
| Sonnet 5 | $0.00005 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
generated-assets 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 6d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated Assets
The README GIF and the social preview card are rendered from the real server, not drawn by hand. That is what makes them trustworthy, and also what makes them a maintenance hazard: they assert things about the product inside pixels, where no reviewer proofreads them. A stale demo is worse than none, because it is a confident claim that is quietly wrong.
Use When
- Changing the name, output shape, or wording of any tool the demo shows
- Changing money formatting, or anything else in
models/amounts.py - Adding or removing tools, which moves the count on the card
- Changing the project's name, tagline, or headline value proposition
- Editing anything under
scripts/demo/ - Preparing a release, as a final check
What exists
| Path | What it is |
|---|---|
assets/demo.gif |
README demo, ~13s, referenced by absolute URL so it also renders on PyPI |
assets/social-preview.png |
1280×640 card for GitHub's social preview and link unfurls |
assets/manifest.json |
The claims the assets make, recorded so drift is detectable |
scripts/demo/backend.py |
A synthetic YNAB API the demo runs against |
scripts/demo/capture.py |
Invokes the real tools, saves what they return |
scripts/demo/social.py |
Renders the card |
scripts/demo/gif.py |
Renders the GIF frames and assembles them |
scripts/check_assets.py |
Compares the recorded claims against live code |
Re-rendering
brew install librsvg imagemagick # once
make assets # capture, render both, record the claims
make assets-check # fail if the claims have gone stale
make assets-check runs in make check, so drift fails the build rather than
shipping. It compares the claims — tool count, which tools appear, the money
format — not the pixels. Byte comparison would be stricter and useless: the
renderers are deterministic, but ImageMagick and font rendering are not stable
across machines, and a check that fails for the wrong reason gets muted.
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.
- 6d ago First seen · 87 lines · 26 tokens per session scan A 801a7c4eb2e7
generated-assets is a skill published in the GitHub repository hs737/mcp-server-for-ynab (1 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 957 once invoked, about $0.0001 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
gpt-image-gen
MUST read before generating images. Detailed prompt-crafting guide for gpt-image models, covering tool routing (native imagegeneration server tool vs the generateimage tool), prompt structure from subject to background, verbatim text rendering, anti-patterns, and the revisedprompt feedback loop for iteration.
twitch-webhooks
Receive and verify Twitch EventSub webhooks. Use when setting up Twitch webhook handlers, debugging signature verification, handling the webhookcallbackverification challenge, or handling EventSub events like stream.online, stream.offline, channel.follow, channel.subscribe, and…
maya-scripting
Bootstrap stage — escape hatch for Maya work that has no packaged skill yet. Agents should prefer searchskills / dcccapabilitymanifest → loadskill → typed tools (inputSchema + annotations) from domain skills; use executepython or executemel only when no skill matches, for bulk in-process loops, or for API…
dcc-mcp-maya-setup
Set up dcc-mcp-maya for an agent or operator: install Maya Python dependencies with mayapy, generate MCP host configuration, guide the user through loading the Maya plugin, and run a first live-tool smoke prompt.
threebrowser-studio-mcp
Author, inspect, render, validate, animate, and save Three.js WebGPU projects in the native ThreeBrowser Studio through its real threestudio MCP tools. Use whenever Codex is asked to build or edit a ThreeBrowser Studio scene, material, Blender-style shader or texture graph, animation, lighting setup, camera, or…
avenox-graphics
Avenox Studio — produce brand-locked motion graphics with HyperFrames and composite them onto a cut video. Use when making cutaway/overlay graphics: title cards, diagrams, data-viz, loops, lower-thirds, outro. Proven cutaway + composite recipe with gotchas. Triggers: "make graphics", "add an animation", "motion…