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/michael-obele/docshark/copilot-instructionsgit clone --depth 1 https://github.com/Michael-Obele/docsharkWrote 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/michael-obele/docshark/copilot-instructions)<a href="https://agentmods.dev/instructions/michael-obele/docshark/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/michael-obele/docshark/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 | $0.02719 | $0.02719 |
| Opus 5 | $0.01359 | $0.01359 |
| Sonnet 5 | $0.00544 | $0.00544 |
| Haiku 4.5 | $0.00272 | $0.00272 |
Grade A, and why
docshark 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.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docshark Site — Copilot Instructions
Copilot quick reference for the Docshark documentation site (SvelteKit + Tailwind CSS v4).
Tech Stack & Architecture
| Tool | Version | Purpose |
|---|---|---|
| Runtime | Bun | Preferred package manager and task runner (bun, bunx) |
| Svelte | 5.51+ | Framework (runes only: $state, $props, $derived, $effect) |
| SvelteKit | 2.50+ | Meta-framework, file-based routing, adapters |
| TypeScript | 5.9+ | Strict type checking required |
| Tailwind CSS | 4.1+ | Vite-integrated. Prefer semantic classes & tokens. NEVER use gradients. |
| Components | Bits UI / shadcn | Headless primitives (Bits UI) and shadcn-style UI components |
| Icons | @lucide/svelte | Use @lucide/svelte ONLY (not lucide-svelte). Import icons as components. |
| MDSvex | 0.12+ | Markdown preprocessor for .svx files |
| Netlify Adapter | 6.0+ | SSR + serverless deployment |
Essential Commands
bun run dev # Start dev server
bun run build # Production build → build/ directory
bun run check # Type check + svelte-check
bun run check:watch # Watch mode type checking
bun run preview # Test production build locally
Coding Conventions
Quality Gate
- Formatting: Format ONLY edited files using
bunx prettier --write <file_path>. Verify with--check. Avoid full-project formatting. - Proactive Checking: Run
bun run checkimmediately after substantive edits to catch regressions or type errors. - Error Handling: Only warnings can be ignored; errors must be fixed immediately. Use
<svelte:boundary>for async operations to handle loading and error states gracefully.
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 · 241 lines · 2,719 tokens per session scan A 1751201b2709
docshark copilot-instructions.md is an instructions file published in the GitHub repository Michael-Obele/docshark (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,719 tokens to every session, about $0.0136 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
liam CLAUDE.md
Instructions for liam-hq/liam, covering claude.md, essential commands, app-specific commands, run only the main web app (port 3001) and format code.
liam AGENTS.md
Instructions for liam-hq/liam, covering repository guidelines, project structure & modules, build, test, and development, coding style & naming and testing guidelines.
alcove AGENTS.md
Instructions for epicsagas/alcove, covering claude.md, repository purpose, actual location, structure and karpathy 3-layer architecture.
documcp copilot-instructions.md
Instructions for tosin2013/documcp, covering documcp ai coding agent instructions, architecture essentials, mcp server design (src/index.ts), tool implementation pattern and knowledge graph memory (src/memory/).
cudaq-docs-mcp CLAUDE.md
Claude Code instructions for rogerawong/cudaq-docs-mcp, covering cudaq-docs-mcp, commands, architecture and constraints.
mcp-itglue CLAUDE.md
Claude Code instructions for mspstack/mcp-itglue, covering mcp-itglue, commands, architecture and conventions.