instruction-routing

instruction-routing is a cursor rule for Cursor from cam-douglas/agent-instructions. It costs 60 tokens per session, scanned A, original, MIT.

A rule system that activates detailed instruction files through an INSTRUCTIONS.md index.

In plain words
What is it for?
It helps route repository instructions based on the request or the project's current state.
Why use it?
It keeps each coding task focused by loading only the instructions that apply instead of reading every rule on every turn.

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/cam-douglas/agent-instructions/instruction-routing
Clone the repo
git clone --depth 1 https://github.com/cam-douglas/agent-instructions

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 instruction-routing

README.md
[![agentmods](https://agentmods.dev/badge/rules/cam-douglas/agent-instructions/instruction-routing.svg)](https://agentmods.dev/rules/cam-douglas/agent-instructions/instruction-routing)
Your own site
<a href="https://agentmods.dev/rules/cam-douglas/agent-instructions/instruction-routing"><img src="https://agentmods.dev/badge/rules/cam-douglas/agent-instructions/instruction-routing.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 This file is loaded in full into every session.
When invoked 60 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 $0.00060 $0.00060
Opus 5 $0.00030 $0.00030
Sonnet 5 $0.00012 $0.00012
Haiku 4.5 $0.00006 $0.00006

Measured 4d ago against content hash d460d97be07e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

instruction-routing 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 4d 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/instruction-routing.mdc · 7 lines

What it actually says

Read /INSTRUCTIONS.md every substantive turn. Load only instruction files whose activation conditions match the request or are listed in STATE.md. Register future instruction files in the index rather than expanding always-on rules.

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. 4d ago First seen · 7 lines · 60 tokens per session scan A d460d97be07e

Subscribe to this mod's changes

instruction-routing is a cursor rule published in the GitHub repository cam-douglas/agent-instructions (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session, about $0.0003 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.