What is debugssy AGENTS.md?

A project guide for Debugssy, a VS Code extension that lets an AI assistant inspect and control a program while it is being debugged. It explains the extension’s structure, files, dependencies, and key concepts.

Use it when adding or changing VS Code commands, MCP server features, debugging tools, settings, validation, or debugger communication.

It gives an AI coding agent the context needed to understand where debugging features live and how the parts connect. This reduces guesswork when changing or troubleshooting the extension.

How gmaynez/debugssy configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to gmaynez/debugssy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/gmaynez/debugssy/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/gmaynez/debugssy

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gmaynez/debugssy/agents-md/github.svg)](https://agentmods.dev/instructions/gmaynez/debugssy/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/gmaynez/debugssy/agents-md"><img src="https://agentmods.dev/badge/instructions/gmaynez/debugssy/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gmaynez/debugssy/agents-md"><img src="https://agentmods.dev/badge/instructions/gmaynez/debugssy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,686 This file is loaded in full into every session.

When invoked 2,686 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02686	$0.02686
Opus 5.5	$0.01074	$0.01074
Sonnet 5.5	$0.00537	$0.00537
Haiku 4.5	$0.00269	$0.00269

Measured 15d ago against content hash 856cfb532e6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

debugssy 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 15d 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.

AGENTS.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugssy - LLM Context

VS Code extension: MCP server exposing DAP (Debug Adapter Protocol) for AI-assisted debugging. Flow: AI Assistant → MCP Protocol → Debugssy → VS Code Debug API → Debugger

Architecture

extension.ts → MCPServer.ts → [ToolRouter, PromptHandler, CompletionProvider, ResourceProvider]
                    ↓
              security/ (McpRequestValidator, ExpressionValidator)
                    ↓
              tools/ (Breakpoints, Inspection, DebugControl)
                    ↓
              dap/Client.ts (DAP message interception, state tracking)

File Map

File	Purpose	Modify When
`extension.ts`	Entry point, lifecycle, commands, MCP auto-discovery (VS Code + Cursor)	Adding VS Code commands or MCP discovery
`types/cursor.d.ts`	Type augmentation for Cursor's `vscode.cursor.mcp` API	Cursor MCP API changes
`MCPServer.ts`	HTTP server, MCP SDK, session mgmt	Adding MCP capabilities
`Config.ts`	Zod-validated settings	Adding config options
`constants.ts`	All magic numbers	Adding limits/defaults
`routing/ToolRouter.ts`	Tool routing, validation	Adding/modifying tools
`routing/PromptHandler.ts`	MCP prompts	Adding prompts
`routing/CompletionProvider.ts`	Autocomplete	Adding completions
`routing/schemas/*.ts`	Tool JSON schemas	Adding tool parameters
`routing/types/toolArguments.ts`	Zod validators + TS types	Adding tool arg types
`security/ExpressionValidator.ts`	Expression safety	Adding language support
`security/expression/validators/*.ts`	Per-language validators	Language-specific rules
`tools/Breakpoints.ts`	Breakpoint ops	Breakpoint features
`tools/Inspection.ts`	Variable/stack inspection	Inspection features
`tools/DebugControl.ts`	Start/stop/step	Execution control
`dap/Client.ts`	DAP interception, state	DAP event handling
`errors/index.ts`	Custom error types with codes	Adding new error types

Read the full file on GitHub · 283 lines

Changes

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.

15d ago Changed · +13 lines · +213 tokens per session 856cfb532e6c
2mo ago First seen · 270 lines · 2,473 tokens per session scan A fa2f26ec72b5

Subscribe to this mod's changes

debugssy AGENTS.md is an instructions file published in the GitHub repository gmaynez/debugssy (20 stars, last pushed 15d ago), licensed Apache-2.0. It adds 2,686 tokens to every session, about $0.0107 per session on Opus 5.5. 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.

Debugging ai mcp

debugssy AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
debugssy AGENTS.mdgmaynez/debugssy	Instructions file	20	15d ago	Apache-2.0	A	2,686	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

debugssy: Instructions file for Codex