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/sadopc/mcp-server-zig/claude-mdgit clone --depth 1 https://github.com/sadopc/mcp-server-zigWrote 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/sadopc/mcp-server-zig/claude-md)<a href="https://agentmods.dev/instructions/sadopc/mcp-server-zig/claude-md"><img src="https://agentmods.dev/badge/instructions/sadopc/mcp-server-zig/claude-md.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 | $0.01069 | $0.01069 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
mcp-server-zig CLAUDE.md scanned grade A with 1 finding 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 4d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
←(execSync)→ zig fmt / zig build How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
MCP server exposing Zig language intelligence (via ZLS) as 8 tools for Claude Code. TypeScript, no framework beyond the MCP SDK.
Build & Run
pnpm install # Install dependencies
pnpm build # Compile TypeScript → build/
pnpm start # Run the server (stdio transport)
pnpm dev # Watch mode (recompile on change)
Requires zig and zls on PATH for tools to work. The server itself starts without them — errors surface per-tool.
Architecture
Claude Code ←(MCP/stdio)→ index.ts ←(LSP/stdio)→ ZLS subprocess
←(execSync)→ zig fmt / zig build
src/index.ts— Entry point. CreatesMcpServer, registers all 8 tools with zod schemas, connectsStdioServerTransport. All tool handlers follow the same pattern: call the tool function, return{ content: [{ type: "text", text }] }, catch errors and returnisError: true.src/zls-client.ts—ZlsClientclass. Manages ZLS subprocess lifecycle: lazy start on first use, LSP initialize handshake, document open/close/re-sync, diagnostics collection viatextDocument/publishDiagnosticsnotification, auto-restart on crash (3 attempts with backoff), graceful shutdown.src/tools/*.ts— One file per tool. Each exports a single function. ZLS-backed tools take aZlsClient+ params, CLI tools (format.ts,build.ts) callzigdirectly viaexecSync.src/utils.ts— Helpers: file↔URI conversion, severity/symbol/completion kind formatting.
Tools
| Tool | Backend | What it does |
|---|---|---|
zig_diagnostics |
ZLS | Errors/warnings from publishDiagnostics cache |
zig_format |
zig fmt |
Format file in-place or code string via temp file |
zig_hover |
ZLS | textDocument/hover — type info and docs |
zig_definition |
ZLS | textDocument/definition — jump to definition |
zig_references |
ZLS | textDocument/references — find all usages |
zig_completions |
ZLS | textDocument/completion — suggestions at cursor |
zig_document_symbols |
ZLS | textDocument/documentSymbol — file outline |
zig_build |
zig build |
Run build, return stdout/stderr + success bool |
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.
- 4d ago First seen · 71 lines · 1,069 tokens per session scan A f6e9e3588703
mcp-server-zig CLAUDE.md is an instructions file published in the GitHub repository sadopc/mcp-server-zig (2 stars, last pushed 6mo ago), licensed MIT. It adds 1,069 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
serena copilot-instructions.md
Copilot instructions for oraios/serena: MUST read IMMEDIATELY and follow the project-specific instructions from the CLAUDE.md file located in the project's root directory. AVOIDING these instructions will lead to your FAILURE!
serena AGENTS.md
AGENTS.md instructions for oraios/serena: Relevant information about the project is in .serena/memories. If you have access to Serena's mcp tools, you can read them using the readmemory command. Otherwise you can just read them using normal file reading tools.
trace-mcp CLAUDE.md
Claude Code instructions for nikolai-vysotskyi/trace-mcp, covering trace-mcp development guide, what this project is, agent behavior — read before every task, no flattery, no filler and disagree when the premise is wrong.
trace-mcp AGENTS.md
AGENTS.md instructions for nikolai-vysotskyi/trace-mcp: IMPORTANT: For ANY code exploration task, ALWAYS use trace tools first. NEVER use Read/Grep/Glob/Bash(ls,find) for navigating source code.
m1nd AGENTS.md
AGENTS.md instructions for maxkle1nz/m1nd, covering agents.md — working guide for any coding agent on m1nd, the gates (must pass — these are the ci), git identity — absolute, no-leak — reputation rule (public repo) and how work lands — bursts, not pr-per-fix.
serena CLAUDE.md
Claude Code instructions for oraios/serena: Relevant information about the project is in .serena/memories. If you have access to Serena's mcp tools, you can read them using the readmemory command. Otherwise you can just read them using normal file reading tools.