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 instructions/robcsaszar/frontend-kit/agents-mdgit clone --depth 1 https://github.com/robcsaszar/frontend-kitWhat 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 | $0.00499 | $0.00499 |
| Opus 5 | $0.00249 | $0.00249 |
| Sonnet 5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
frontend-kit AGENTS.md 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 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.
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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Mission
This repo publishes the frontend-kit skill collection: four independent skills under skills/<name>/, each covering one frontend implementation area (canvas, drag-and-drop, Svelte 5 / SvelteKit, SVG animation). There is no build, no tests, no runtime of its own. The deliverable is the contents of skills/*. This repo's purpose is publishing copies of skills for others to install into their own projects, not authoring net-new guidance from scratch. Changes should be judged by: would a stranger who installs one of these skills into an unrelated project get correct, generically useful frontend guidance out of it?
Layout convention
- One directory per skill under
skills/<name>/,name:in frontmatter matching the directory name exactly. - Each skill is self-contained: its own
SKILL.mdplus anyreferences/it needs. No skill depends on another skill in this collection being installed. - No skill in this collection ships a
scripts/directory. If one is ever added, it needs aSAFETY.mdat the repo root documenting what the script does, per the same convention used in this author's other skill repos.
Judgment boundaries
NEVER:
- Never let a copied skill's content leak repo-specific references back to Orakl (or any other single project it may have been sourced from): file paths, project names, internal conventions. These skills need to read as generic frontend guidance, usable in any codebase.
ASK:
- Ask before removing a skill from the collection.
- Ask before changing the license or copyright holder.
ALWAYS:
- When adding, removing, or renaming a skill: update the table in
README.mdin the same change.
Adding a skill
- Copy the skill's full directory (
SKILL.mdplusreferences/,assets/,scripts/as applicable) intoskills/<name>/, matching the frontmattername:to the directory name. - Grep the copy for any project-specific leakage (source repo name, absolute paths, internal doc references) before publishing; flag anything found rather than silently editing the skill's content.
- Add a row to the table in
README.md. - If the skill ships a script, add a
SAFETY.mdat the repo root and link it fromREADME.md.
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 · 31 lines · 499 tokens per session scan A 87d3b222cdbb
frontend-kit AGENTS.md is an instructions file published in the GitHub repository robcsaszar/frontend-kit (1 stars, last pushed 2d ago), licensed MIT. It adds 499 tokens to every session, about $0.0025 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 instructions, from other repositories
pocketbase-sveltekit-starter AGENTS.md
Instructions for spinspire/pocketbase-sveltekit-starter, covering agents, project structure, dev mode, deployment and key commands.
ssgoi AGENTS.md
Instructions for meursyphus/ssgoi, covering ssgoi and releasing.
svelte-markdown CLAUDE.md
Instructions for humanspeak/svelte-markdown, covering claude.md, project overview, key technologies, project structure and development commands.
sveltest AGENTS.md
Instructions for spences10/sveltest, covering agents.md, unbreakable rules, essential commands, development and testing.
neo-svelte copilot-instructions.md
Instructions for dvcol/neo-svelte, covering examples old vs new, redirect and error handling, cookie path requirement, top-level promise handling and goto changes.
neo-svelte AGENTS.md
Instructions for dvcol/neo-svelte: Pick the guide that matches your task — load only the slice you need.