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/digitarald/vscode-agent-todos/copilot-instructionsgit clone --depth 1 https://github.com/digitarald/vscode-agent-todosWrote 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/digitarald/vscode-agent-todos/copilot-instructions)<a href="https://agentmods.dev/instructions/digitarald/vscode-agent-todos/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/digitarald/vscode-agent-todos/copilot-instructions.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 | $0.05378 | $0.05378 |
| Opus 5 | $0.02689 | $0.02689 |
| Sonnet 5 | $0.01076 | $0.01076 |
| Haiku 4.5 | $0.00538 | $0.00538 |
Grade A, and why
vscode-agent-todos copilot-instructions.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 — 729 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
This extension provides VS Code agent mode with todo management tools through MCP (Model Context Protocol) and an integrated VS Code tree view. It enables AI assistants to proactively track tasks during development workflows with support for subtasks, priorities, auto-injection into Copilot instructions.
For more details:
- Main README - Feature overview and usage
- MCP Server Documentation - Server architecture, protocol details, and completion support
- MCP TypeScript SDK
IMPORTANT:
- ALWAYS plan changes using detailed todos
- ALWAYS keep
.github/copilot-instructions.mdup-to-date with the latest architecture and coding standards, addressing any drifts in implementation! - ALWAYS validate changes by running compile and test commands!
- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.
- NEVER make changes backwards compatible unless explicitly requested by the User.
- NEVER create one-off scripts to test changes.
Architecture
graph TB
subgraph VSCodeExtension[VS Code Extension]
EXT[Extension Entry<br/>extension.ts]
TM[TodoManager<br/>Singleton]
TTP[TodoTreeProvider]
TDP[TodoDecorationProvider]
SM[SubtaskManager<br/>Static Methods]
TV[TodoValidator<br/>Static Methods]
PM[PerformanceMonitor<br/>Static Class]
end
subgraph StorageLayer[Storage Layer]
ITS[ITodoStorage<br/>Interface]
WSS[WorkspaceStateStorage<br/>Default]
IMS[InMemoryStorage<br/>Testing/Standalone]
end
subgraph ExportLayer[Export Layer]
CIM[CopilotInstructionsManager<br/>Write-only Export]
SCW[StandaloneCopilotWriter<br/>Write-only Export]
end
subgraph MCPIntegration[MCP Integration]
MCP[TodoMCPServerProvider]
MCPS[TodoMCPServer<br/>HTTP/SSE]
TT[TodoTools<br/>read/write handlers]
TS[TodoSync<br/>Bidirectional]
STM[StandaloneTodoManager<br/>Singleton]
subgraph SessionMgmt[Session Management]
TRM[Transports Map]
SRM[Servers Map]
STR[StreamableHTTPServerTransport]
end
end
subgraph ExternalInterfaces[External Interfaces]
VSC[VS Code API]
CI[todos.instructions.md]
MC[MCP Clients<br/>AI Assistants]
MCPAPI[VS Code MCP API]
end
%% Core initialization
EXT --> TM
EXT --> TTP
EXT --> TDP
EXT --> MCP
%% Storage configuration
TM --> WSS
STM --> IMS
WSS -.-> ITS
IMS -.-> ITS
MCP --> WSS
%% UI and decorations
TTP --> VSC
TDP --> VSC
TM --> TTP
TM --> TDP
%% View events
TM -.->|onShouldOpenView| EXT
TM -.->|onDidChange| TTP
%% Export to markdown (write-only)
TM -.->|auto-inject writes| CIM
CIM -->|write-only| CI
STM -.->|auto-inject writes| SCW
SCW -->|write-only| CI
%% MCP server setup
MCP --> MCPS
MCP --> MCPAPI
MCPS --> TT
MCPS --> STR
STR --> TRM
STR --> SRM
%% Bidirectional sync
MCP --> TS
TS <--> TM
TS <--> STM
%% Tool handling
TT --> STM
TT --> TS
%% External communication
MC <-->|HTTP POST/GET/SSE| MCPS
%% Utility usage
TM --> SM
TM --> TV
TM -.-> PM
STM --> TV
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 · 729 lines · 5,378 tokens per session scan A 802ece31c520
vscode-agent-todos copilot-instructions.md is an instructions file published in the GitHub repository digitarald/vscode-agent-todos (39 stars, last pushed 11mo ago), licensed MIT. It adds 5,378 tokens to every session, about $0.0269 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
memorix CLAUDE.md
Claude Code instructions for AVIDS2/memorix, covering memorix - agent instructions for claude code, using memorix memory tools, when to search memory, when to store memory and when to resolve memory.
memorix GEMINI.md
Gemini CLI instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.
bootstrap-alwayson
Minimal always-required LLM fixes.
rosetta AGENTS.md
AGENTS.md instructions for griddynamics/rosetta: Main goal: cover E2E AI PDLC engineering workflows at foundation level for AI-First SDLC in enterprise. Top-level or orchestrator agents MUST READ docs/ARCHITECTURE.md contains technical details and guidance, and docs/CONTEXT.md - business context. Subagents - when…
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
rosetta pr-review-bots.instructions.md
How Copilot and CodeRabbit reviews manifest on a rosetta PR, why each looks different from a gh point of view, and what 'wrapping a PR' actually requires.