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/kioie/tiny-go-mcp-server/agents-mdgit clone --depth 1 https://github.com/kioie/tiny-go-mcp-serverWrote 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/kioie/tiny-go-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/kioie/tiny-go-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/kioie/tiny-go-mcp-server/agents-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 | $0.01088 | $0.01088 |
| Opus 5 | $0.00544 | $0.00544 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
tiny-go-mcp-server 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 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions (Tiny Go MCP Server)
Guidance for AI coding agents working in this repository. For a compact, token-efficient API cheat sheet (including when generating code outside this repo), see SYSTEM_PROMPT.md.
Commands
- Test all:
make testorgo test -race ./... - Test package:
go test -race -v ./tinymcp - Test single:
go test -run TestName ./path/to/pkg -v - Lint:
make lint(requires golangci-lint) - Lint tool descriptions:
make lint-tools(AGENTS.md when/when-not/siblings pattern) - Coverage:
make coverage(all packages) ormake coverage-check(70% gate on tinymcp + cmd) - Build example server:
make build→./tiny-go-mcp - Minimal example:
go run ./examples/minimal - HTTP example:
go run ./examples/http(listens on:8080, override withTINY_GO_MCP_ADDR) - HTTP deploy / Smithery URL:
go run ./examples/http-deploy— seedocs/SMITHERY.md - Resources/prompts example:
go run ./examples/resources
Layout
tinymcp/— importable library (github.com/kioie/tiny-go-mcp-server/tinymcp)cmd/tiny-go-mcp/— reference MCP server (add, subtract, greet tools)examples/minimal/— smallest possible server for copy-paste
API notes
- Tool registration:
tinymcp.RegisterTool(server, name, desc, handler)orRegisterToolDeffor fullmcp.Toolmetadata — returns errors for nil server and invalid tool definitions (no panics). UseMustRegisterTool/MustRegisterPromptat startup to panic on misconfiguration. - Registration errors:
errors.Is(err, tinymcp.ErrNilServer),ErrNilTool,ErrNilHandler,ErrRegistrationFailed— do not string-match. - Resource/prompt registration: nil handlers return errors at registration time; nil server is reported before nil handler.
- Server options:
NewServer(name, ver, tinymcp.WithInstructions(...))orNewServerWithOptions(name, ver, &mcp.ServerOptions{...}); full control viaRawServer(). - Handlers need both
tinymcpandgithub.com/modelcontextprotocol/go-sdk/mcpimports. - HTTP middleware:
tinymcp.WithCrossOriginProtection,tinymcp.BearerTokenAuth,tinymcp.DisableLocalhostProtectionFromEnv,HTTPOptions.WithMiddleware— seeexamples/http-deploy. - HTTP lifecycle:
ListenAndServeHTTPdrains on SIGINT/SIGTERM;ListenAndServeHTTPContext/StartHTTPContextfor custom shutdown — seedocs/HTTP.md. - Optional server logs: set env
TINY_GO_MCP_VERBOSE=1(stderr only; stdio is reserved for MCP). - HTTP/SSE:
StartHTTP,StartSSE,StreamableHTTPHandler,SSEHandler— seedocs/HTTP.md. - Resources:
RegisterResource,RegisterResourceTemplate,RegisterTextResource,TextResource - Prompts:
RegisterPrompt,PromptResult,UserPromptMessage,AssistantPromptMessage
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 · 64 lines · 1,088 tokens per session scan A 4aba9551469d
tiny-go-mcp-server AGENTS.md is an instructions file published in the GitHub repository kioie/tiny-go-mcp-server (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,088 tokens to every session, about $0.0054 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
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
sigmap AGENTS.md
AGENTS.md instructions for manojmallick/sigmap, covering sigmap — agents.md, append strategy (required), auto-generated signatures, code signatures and sigmap commands.
gollem CLAUDE.md
Instructions for gollem-dev/gollem, covering claude.md, restriction & rules, commands, development and testing and test execution.
gitlab-mcp-server mcp-best-practices.instructions.md
MCP protocol-level best practices for tool design, annotations, response formats, pagination, and security. Applies to all Go MCP server code.
gitlab-mcp-server security-and-owasp.instructions.md
Comprehensive secure coding instructions for all languages and frameworks, based on OWASP Top 10 and industry best practices.
wanwu-workflow CLAUDE.md
Instructions for UnicomAI/wanwu-workflow, covering claude.md, project overview, development commands, environment setup and clone and setup.