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.
git clone --depth 1 https://github.com/Kodaxadev/Task-Anchor-MCPWrote 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/rules/kodaxadev/task-anchor-mcp/task-anchor)<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/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.
<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="Reviewed on agentmods" width="80" 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 | $0.00345 | $0.00345 |
| Opus 5.5 | $0.00138 | $0.00138 |
| Sonnet 5.5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00034 | $0.00034 |
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 1mo 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.
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
- You CANNOT write, edit, or create files until
task_lock_statusreturns ACTIVE - You MUST call
drift_detecton every user message before responding - You MUST call
scope_validate_editbefore modifying any file - If
task_lock_statusshows 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, calltask_lock_status. - During: Call
drift_detecton every user turn. Callparked_addfor any tangents. - End:
session_checkpointis MANDATORY before ending any work session.
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.
- 1mo ago First seen · 45 lines · 345 tokens per session scan A cb17e7e2cccc
task-anchor is a cursor rule published in the GitHub repository Kodaxadev/Task-Anchor-MCP (3 stars, last pushed 5mo ago), licensed MIT. It adds 345 tokens to every session, about $0.0014 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 2026-08-31.
Other cursor rules, from other repositories
always-push-pr
Always commit, push, and open or update a PR for work in this repo.
agent-efficiency
Agent-mode tool-call efficiency. Cuts the largest hidden cost in modern AI IDEs — wasted tool calls and oversized context windows.
squirrel-mode
ADHD-friendly response rules for squirrel-mode - answer first, zero fluff.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.