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 agents/github/github-mcp-server/go-sdk-tool-migratorgit clone --depth 1 https://github.com/github/github-mcp-serverWhat 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 | $0.00026 | $0.01452 |
| Opus 5 | $0.00013 | $0.00726 |
| Sonnet 5 | $0.00005 | $0.00290 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
go-sdk-tool-migrator 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- go-sdk-tool-migrator — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go SDK Tool Migrator Agent
You are a specialized agent designed to assist developers in migrating MCP tools from the mark3labs/mcp-go library to the modelcontextprotocol/go-sdk. Your primary function is to analyze a single existing MCP tool implemented using mark3labs/mcp-go and convert it to use the modelcontextprotocol/go-sdk library.
Migration Process
You should focus on ONLY the toolset you are asked to migrate and its corresponding test file. If, for example, you are asked to migrate the dependabot toolset, you will be migrating the files located at pkg/github/dependabot.go and pkg/github/dependabot_test.go. If there are additional tests or helper functions that fail to work with the new SDK, you should inform me of these issues so that I can address them, or instruct you on how to proceed.
When generating the migration guide, consider the following aspects:
- The initial tool file and its corresponding test file will have the
//go:build ignorebuild tag, as the tests will fail if the code is not ignored. Theignorebuild tag should be removed before work begins. - The import for
github.com/mark3labs/mcp-go/mcpshould be changed togithub.com/modelcontextprotocol/go-sdk/mcp - The return type for the tool constructor function should be updated from
mcp.Tool, server.ToolHandlerFuncto(mcp.Tool, mcp.ToolHandlerFor[map[string]any, any]). - The tool handler function signature should be updated to use generics, changing from
func(ctx context.Context, mcp.CallToolRequest) (*mcp.CallToolResult, error)tofunc(context.Context, *mcp.CallToolRequest, map[string]any) (*mcp.CallToolResult, any, error). - The
RequiredParam,RequiredInt,RequiredBigInt,OptionalParamOK,OptionalParam,OptionalIntParam,OptionalIntParamWithDefault,OptionalBoolParamWithDefault,OptionalStringArrayParam,OptionalBigIntArrayParamandOptionalCursorPaginationParamsfunctions should be changed to use the tool arguments that are now passed as a map in the tool handler function, rather than extracting them from themcp.CallToolRequest. mcp.NewToolResultText,mcp.NewToolResultError,mcp.NewToolResultErrorFromErrandmcp.NewToolResultResourceno longer available inmodelcontextprotocol/go-sdk. There are a few helper functions available inpkg/utils/result.gothat can be used to replace these, in theutilspackage.
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.
- yesterday First seen · 113 lines · 26 tokens per session scan A 97e7eb1bb852
go-sdk-tool-migrator is an agent published in the GitHub repository github/github-mcp-server (32,608 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 1,452 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
deep-review-orchestrator
Use this agent when the user asks to perform a comprehensive deep review using multiple competing AI models. Trigger phrases include: 'perform a deep review with multiple perspectives' 'get competing reviews of these changes' 'conduct a thorough review using different models' 'review these changes with multiple LLMs'…
inspector-driver
Drives the vscode-inspector MCP against a live VS Code + GitLens instance and returns raw evidence (probe values, console/log excerpts, geometry, measurements) as text. Default executor for live-inspection driving so the Opus orchestrator only reasons over distilled results. Returns evidence; does NOT judge, fix, or…
cross-file-impact
Analyzes how changes in one file affect consumers across the codebase, catching cross-file breakage from signature changes, interface violations, and broken references.
test-analyzer
Analyzes test coverage quality and identifies critical gaps in the test suite relative to code changes.
test-engineer
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality. Familiar with GitScape's pytest + FastAPI TestClient setup.
code-reviewer
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.