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/zircote/markdown-lsp/copilot-instructionsgit clone --depth 1 https://github.com/zircote/markdown-lspWhat 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 | $0.00115 | $0.00115 |
| Opus 5 | $0.00057 | $0.00057 |
| Sonnet 5 | $0.00023 | $0.00023 |
| Haiku 4.5 | $0.00012 | $0.00012 |
Grade A, and why
markdown-lsp 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 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.
What it actually says
Copilot instructions
You are working in a template repository for Claude Code + MCP servers.
Priorities
- Keep changes small and reviewable.
- Prefer TypeScript and the official
@modelcontextprotocol/sdk. - Update documentation when you change developer-facing behavior.
Commands
- Build:
npm run build - Typecheck:
npm run typecheck - Run MCP server (dev):
npm run dev
Security
- Never hardcode tokens.
- Prefer env vars in
.mcp.json/ Claude Desktop config.
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 · 21 lines · 115 tokens per session scan A 52897829f8eb
markdown-lsp copilot-instructions.md is an instructions file published in the GitHub repository zircote/markdown-lsp (3 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session, about $0.0006 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
agent-lsp CLAUDE.md
Instructions for blackwell-systems/agent-lsp, a project described as: MCP server that orchestrates language servers into agent-native workflows. 65 tools, 30 CI-verified languages.
solidity-language-server AGENTS.md
Instructions for asyncswap/solidity-language-server, covering agents, prerequisites: ast identity model, the two id types, the src string format and why file ids are unstable from solc.
csharp-lsp CLAUDE.md
Instructions for zircote/csharp-lsp, covering claude.md, project overview, setup, key files and conventions.
svelte-lsp CLAUDE.md
Instructions for zircote/svelte-lsp, covering claude.md, project overview, setup, global lsp server and project development tools.
cpp-lsp CLAUDE.md
Instructions for zircote/cpp-lsp, covering claude.md, project overview, setup, key files and conventions.
python-lsp CLAUDE.md
Instructions for zircote/python-lsp, covering claude.md, project overview, setup, key files and hook system.