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.

In plain words
What is it for?
Use it when adding or changing VS Code commands, MCP server features, debugging tools, settings, validation, or debugger communication.
Why use it?
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.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/gmaynez/debugssy/agents-md
Clone the repo
git clone --depth 1 https://github.com/gmaynez/debugssy

Made for: Codex, OpenCode.

Per session 2,473 This file is loaded in full into every session.
When invoked 2,473 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.02473 $0.02473
Opus 5 $0.01236 $0.01236
Sonnet 5 $0.00495 $0.00495
Haiku 4.5 $0.00247 $0.00247

Measured 3d ago against content hash fa2f26ec72b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

AGENTS.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 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 · 270 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.

  1. 3d 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 3mo ago), licensed Apache-2.0. It adds 2,473 tokens to every session, about $0.0124 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens