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/oguzhankir/fmtly/copilot-instructionsgit clone --depth 1 https://github.com/oguzhankir/fmtlyWrote 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/instructions/oguzhankir/fmtly/copilot-instructions)<a href="https://agentmods.dev/instructions/oguzhankir/fmtly/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/oguzhankir/fmtly/copilot-instructions.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 | $0.01066 | $0.01066 |
| Opus 5 | $0.00533 | $0.00533 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
fmtly copilot-instructions.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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- fmtly CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fmtly — Windsurf Rules
Read this file entirely before writing any code.
The Vision
Format, validate, convert, and diff structured data. No login. No server. Instant.
fmtly is not just a random collection of utilities. It is a deep, focused platform for structured data formats (JSON, XML, YAML, CSV, TOML), with a visionary roadmap to expand into AI/LLM toolchains, encoders, code formatters, and more.
The Golden Rule: Every tool runs in the browser. No user data ever touches a server. Exception: Network tools (IP lookup, DNS, etc.) proxy through a minimal Cloudflare Worker without logging.
Stack
- SvelteKit 2 + TypeScript 5 + Tailwind CSS 4
- Cloudflare Pages (static) + Cloudflare Workers (network proxy only)
- Package manager: pnpm — never npm, never yarn
- Adapter:
@sveltejs/adapter-cloudflare
Architecture Rules
Tool Registry
Every tool is a config object in src/lib/registry/tools/[category].tools.ts.
Never create a route file for a tool — register it, the page generates itself.
Category-Based Structure
When adding new tools or categories, strictly adhere to the category-based folder structure:
- Registry:
src/lib/registry/tools/[category].tools.ts - Engines:
src/lib/engines/[category]/(include anindex.tsbarrel file) - Panels:
src/lib/components/panels/[category]/ - Tests:
tests/unit/[category]/ - Stores:
src/lib/stores/[category].store.ts(if state is required) - Locales:
src/lib/i18n/registry/[lang].ts
Never put category-specific logic in shared directories.
Lazy Loading — No Exceptions
Every processing library uses dynamic import(). Never at top level.
This applies to: ajv, js-yaml, fast-xml-parser, smol-toml, @wasm-fmt/taplo_fmt, Monaco Editor, etc.
If it processes data → dynamic import.
No Backend for User Data
Permitted server-side code only:
+page.tsload functions (read registry)/sitemap.xml/+server.ts(build time only)
Static Output Only
No Node.js APIs in browser code (fs, path, crypto module — use Web Crypto API).
No env vars in browser except PUBLIC_ prefix.
Never delete static/_headers, static/_redirects, static/_routes.json.
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.
- 3d ago First seen · 124 lines · 1,066 tokens per session scan A 691884928e6d
fmtly copilot-instructions.md is an instructions file published in the GitHub repository oguzhankir/fmtly (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,066 tokens to every session, about $0.0053 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
AnvilWiki AGENTS.md
AGENTS.md instructions for PNGTRID/AnvilWiki, covering agents.md, repository purpose, read these first, intended tech stack (verified, as of 2026-08-11) and architecture: code/config/content separation (critical).
sighttrue CLAUDE.md
Claude Code instructions for sighttrue/sighttrue, covering sighttrue — unified developer signal agent, non-negotiables, skill routing by phase, cadence and storage layout.
openscreen AGENTS.md
AGENTS.md instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
claude-ads CLAUDE.md
Instructions for AgriciDaniel/claude-ads, covering claude ads repository instructions, architecture, development and verification.