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/rethunk-ai/rethunk-mcp-go/agents-mdgit clone --depth 1 https://github.com/Rethunk-AI/rethunk-mcp-goWrote 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/rethunk-ai/rethunk-mcp-go/agents-md)<a href="https://agentmods.dev/instructions/rethunk-ai/rethunk-mcp-go/agents-md"><img src="https://agentmods.dev/badge/instructions/rethunk-ai/rethunk-mcp-go/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 5.1 | $0.00837 | $0.00837 |
| Opus 5 | $0.00418 | $0.00418 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
rethunk-mcp-go 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 5d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS — rethunk-mcp-go
MCP server for Go language analysis: static analysis, testing, linting, formatting via go vet, go test, golint, go fmt, and related tools.
Repository Purpose
- Users: LLMs (Claude Code, ChatGPT) analyzing and improving Go codebases
- AI Agents: Tool orchestration and error handling for Go toolchain commands
- Maintainers: Go/TypeScript compatibility, security patch management
Contents
src/
├── tools/
│ └── goTools.ts Go CLI tool wrappers (analyze, fix, test)
├── types/ TypeScript interfaces for tool I/O
├── errors/ Custom MCP error classes
└── index.ts MCP server entrypoint
cmd/
└── example/ Go test project for tool validation
package.json Bun build & npm/ts config
README.md User documentation
SECURITY.md Vulnerability reporting & input validation
CONTRIBUTING.md Developer guidelines
Usage
bun install
bun run build # Compile TypeScript → JavaScript
bun run start # Start MCP server (stdio or HTTP)
bun run dev # Watch mode for development
bun run test # Run TypeScript tests
bun run lint # Run Biome linter/formatter
🚨 CRITICAL AI CONSTRAINT
Modifications to command execution paths MUST NOT be made autonomously by AI agents without human review.
- ✅ Agents MAY: fix typos, update docs, improve error messages, refactor non-critical code
- ❌ Agents MUST NOT: modify
executeGoCommand, argument parsing, path resolution, or shell escaping logic without explicit human approval
Reason: executeGoCommand directly invokes shell commands with user-supplied input. Unreviewed changes could:
- Introduce shell injection vulnerabilities
- Enable directory traversal attacks
- Expose sensitive file contents via Go tool output
- Allow arbitrary code execution on the server
All changes to command execution require:
- GitHub pull request for visibility
- Security review focusing on input validation and shell escaping
- Explicit approval before merge
- Test with malicious input payloads before deployment
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.
- 5d ago First seen · 92 lines · 837 tokens per session scan A c10a14282b11
rethunk-mcp-go AGENTS.md is an instructions file published in the GitHub repository Rethunk-AI/rethunk-mcp-go (1 stars, last pushed 1mo ago), licensed MIT. It adds 837 tokens to every session, about $0.0042 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
manifold AGENTS.md
Instructions for intelligencedev/manifold, covering go/manifold, coding conventions, project structure & module organization, package organization and dependency injection.
gitlab-mcp-server go.instructions.md
Instructions for writing Go code following idiomatic Go practices and community standards.
gitlab-mcp-server go-mcp-server.instructions.md
Best practices and patterns for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk package (v1.7.0+).
gitlab-mcp-server AGENTS.md
AGENTS.md instructions for jmrplens/gitlab-mcp-server, covering gitlab-mcp-server — agent quick reference, read first, hard invariants, common commands and build.
gitlab-mcp-server test-goroutines.instructions.md
Testing.T usage rules for code that runs off the test goroutine: HTTP mock handlers, go statements, errgroup tasks, and MCP tool handlers.
gitlab-mcp-server CLAUDE.md
Claude Code instructions for jmrplens/gitlab-mcp-server, covering gitlab-mcp-server — ai development context, project overview, scale, orbit live tests and project structure.