Agent TodosSAFE
Gives VS Code agent mode planning superpowers with dynamic todo lists
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/digitarald/vscode-agent-todos/actions/workflows/auto-release.yml) [](https://github.com/digitarald/vscode-agent-todos/actions/workflows/release.yml) [](https://marketplace.visualstudio.com/items?itemName=digitarald.agent-todos) [](https://marketplace.visualstudio.com/items?itemName=digitarald.agent-todos)
Your AI pair programmer's memory system. Seamlessly integrate persistent task tracking with GitHub Copilot and VS Code's native AI features—giving your coding assistant perfect memory across sessions.
"Finally, an AI assistant that remembers what we planned to do next."
Why Agent TODOs?
VS Code's agent mode is incredibly powerful for code generation and problem-solving. Agent TODOs takes this foundation to the next level by adding advanced workflow management capabilities that transform how agent mode handles complex, multi-session projects.
Agent TODOs upgrades your AI coding experience by adding a persistent memory system that:
- Enhances workflow continuity across sessions, building on VS Code's excellent chat capabilities
- Scales task complexity by adding structured decomposition to complement VS Code's problem-solving power
- Optimizes context efficiency by working alongside VS Code's native AI to manage information flow
- Adds professional tracking with rollback capabilities that extend VS Code's debugging features
Key Features
- 🗺️ Persistent AI Memory: Structured task decomposition that survives session restarts—no more lost context or repeated work
- 📊 Workflow State Management: Three-state
8913036fe83aOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add agent-todos -- npx -y [email protected]
{
"mcpServers": {
"agent-todos": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (2)
1 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
todo_read | read | |
todo_write | write |
Trust audit
SAFEgrade B · trust 88/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (10)
streamable-http
.vscode-test.mjs
.vscodeignore
CLAUDE.md
import { TodoItem } from '../../types';import { TodoValidator } from '../../todoValidator';const packageJson = require('../../package.json');const packageJson = require('../../package.json');import { InMemoryStorage } from '../../storage/InMemoryStorage';@modelcontextprotocol/sdk, @vscode/extension-telemetry, eventsource, express, node-fetch, @types/vscode, @types/express, @types/mocha
Gates applied: no_behavioural_pass.
8913036fe83afull audit observations/trust-audit/mcp-server/digitarald__agent-todos.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 8913036fe83a | SAFE | B | 88 | first audit |
Questions
What is the Agent Todos MCP server?
Gives VS Code agent mode planning superpowers with dynamic todo lists
What tools does Agent Todos expose?
2 in total: 1 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Agent Todos safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (88/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Agent Todos need?
No credential environment variables were found in its source, so it appears to need none.
How does Agent Todos run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as agent-todos at 0.0.2.
How current is this page?
The grade is for one exact copy of the source (8913036fe83a), read on 2026-10-08. The repository is watched and re-audited when it changes.