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/go-delve/mcp-dap-server/claude-mdgit clone --depth 1 https://github.com/go-delve/mcp-dap-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/go-delve/mcp-dap-server/claude-md)<a href="https://agentmods.dev/instructions/go-delve/mcp-dap-server/claude-md"><img src="https://agentmods.dev/badge/instructions/go-delve/mcp-dap-server/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 5.1 | $0.02867 | $0.02867 |
| Opus 5 | $0.01434 | $0.01434 |
| Sonnet 5 | $0.00573 | $0.00573 |
| Haiku 4.5 | $0.00287 | $0.00287 |
Grade A, and why
mcp-dap-server CLAUDE.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 6d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an MCP (Model Context Protocol) server that bridges MCP clients with DAP (Debug Adapter Protocol) debuggers. It exposes debugging capabilities as MCP tools, allowing AI assistants to programmatically control debuggers. Supports Delve (Go) and GDB (C/C++ via native DAP).
Architecture
Core Components
main.go: MCP server initialization
- Creates the MCP server using the
go-sdk - Registers all debugging tools via
registerTools() - Registers workflow prompts via
registerPrompts() - Exposes stdio transport
prompts.go: MCP prompt implementations
- 4 prompt handlers for guided debugging workflows (source, attach, core dump, binary)
- Registered via
server.AddPrompt()— no session state, always available - Each prompt returns a
GetPromptResultwith step-by-step tool invocation guidance
tools.go: MCP tool implementations (~1200 lines)
- All MCP tools are methods on
debuggerSessionstruct - Each tool method signature:
func (ds *debuggerSession) toolName(ctx context.Context, _ *mcp.ServerSession, params *mcp.CallToolParamsFor[ParamsType]) (*mcp.CallToolResultFor[any], error) - Tools send DAP requests via
ds.clientand read/parse responses readAndValidateResponse(client, requestSeq, errorPrefix)matches responses byrequest_seq, skipping unrelated responsesreadTypedResponse[T](client, requestSeq)matches typed responses byrequest_seq, skipping unrelated responses- Tools that wait for stopped/terminated events loop on
ReadMessage()until they receive the expected event
dap.go: DAP client implementation
DAPClientmanages TCP or stdio connection to DAP server- Wraps
github.com/google/go-dapprotocol messages - All DAP request methods return
(int, error)whereintis the request sequence number - Sequence numbers are used to match responses to requests via
request_seqfield
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.
- 6d ago First seen · 246 lines · 2,867 tokens per session scan A d7aca77d920c
mcp-dap-server CLAUDE.md is an instructions file published in the GitHub repository go-delve/mcp-dap-server (101 stars, last pushed 1mo ago), licensed MIT. It adds 2,867 tokens to every session, about $0.0143 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 instructions, from other repositories
neeko AGENTS.md
AGENTS.md instructions for tincopper/neeko, covering neeko — repository guidelines, 项目概览, 目录结构, 前端（feature-based 架构） and 后端（domain-driven 模块化架构）.
neeko CLAUDE.md
Claude Code instructions for tincopper/neeko, covering neeko — claude.md, 项目概览, 常用命令速查, 键盘快捷键 and 预置 agent & ide.
tarsy CLAUDE.md
Claude Code instructions for codeready-toolchain/tarsy, covering project overview, architecture, three-service split, key go packages (pkg/) and data flow.
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
claimidx CLAUDE.md
Claude Code instructions for claimidx/claimidx: This repository is Claimidx — prior art for agents. Failure layer, not a general knowledge base.
AgentStack agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.