task-anchor

task-anchor is a cursor rule for Cursor from Kodaxadev/Task-Anchor-MCP. It costs 345 tokens per session, scanned A, original, MIT.

A task-management rule system for coding sessions, connected through an MCP server. MCP is a way for an agent to use external tools; here, those tools track the active task, distractions, edits, and session checkpoints.

In plain words
What is it for?
Use it to lock a task before editing files, check each request for drift, validate proposed changes, park unrelated ideas, and resume or checkpoint work.
Why use it?
It prevents coding from starting without a clearly defined task and helps detect when work drifts away from the agreed scope. It also records progress between sessions.

Cursor rule for Cursor

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 rules/kodaxadev/task-anchor-mcp/task-anchor
Clone the repo
git clone --depth 1 https://github.com/Kodaxadev/Task-Anchor-MCP

Made for: Cursor.

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.

agentmods badge for task-anchor

README.md
[![agentmods](https://agentmods.dev/badge/rules/kodaxadev/task-anchor-mcp/task-anchor.svg)](https://agentmods.dev/rules/kodaxadev/task-anchor-mcp/task-anchor)
Your own site
<a href="https://agentmods.dev/rules/kodaxadev/task-anchor-mcp/task-anchor"><img src="https://agentmods.dev/badge/rules/kodaxadev/task-anchor-mcp/task-anchor.svg" alt="Measured on agentmods" height="20"></a>
Per session 345 This file is loaded in full into every session.
When invoked 345 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 $0.00345 $0.00345
Opus 5 $0.00172 $0.00172
Sonnet 5 $0.00069 $0.00069
Haiku 4.5 $0.00034 $0.00034

Measured 3d ago against content hash cb17e7e2cccc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-anchor 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.

.cursor/rules/task-anchor.mdc · 45 lines

What it actually says

Task Anchor Enforcement Protocol

This project includes a Task Anchor MCP server. These tools are MANDATORY, not optional.

MCP Config

Add to Cursor MCP settings (Settings → MCP):

{
  "task-anchor": {
    "command": "python",
    "args": ["-m", "task_anchor.server"],
    "cwd": "/absolute/path/to/TaskAnchor/mcp-server"
  }
}

Absolute Rules

  1. You CANNOT write, edit, or create files until task_lock_status returns ACTIVE
  2. You MUST call drift_detect on every user message before responding
  3. You MUST call scope_validate_edit before modifying any file
  4. If task_lock_status shows NO TASK LOCK, refuse all coding help until a lock is created

Enforcement Dialogue

If the user tries to skip task lock:

"I need a task lock before we write any code. What specifically are you building, and what does done look like?"

If drift_detect returns positive:

"I've caught a potential drift. Parking that idea so it's safe — now, back to [current task]."

Session Protocol

  • Start: Call session_resume. If no session, call task_lock_status.
  • During: Call drift_detect on every user turn. Call parked_add for any tangents.
  • End: session_checkpoint is MANDATORY before ending any work session.
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 · 45 lines · 345 tokens per session scan A cb17e7e2cccc

Subscribe to this mod's changes

task-anchor is a cursor rule published in the GitHub repository Kodaxadev/Task-Anchor-MCP (2 stars, last pushed 3mo ago), licensed MIT. It adds 345 tokens to every session, about $0.0017 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 2026-08-31.