09-task-routing

09-task-routing is a cursor rule for Cursor from alieismy/codex-three-layer-delivery. It costs 803 tokens per session, scanned A, original, MIT.

A set of routing rules for eight research and document skills, plus an optional coordinator for work that produces several documents.

In plain words
What is it for?
Use it to decide which skill should handle requirements, feasibility, research, technical proposals, detailed design, standards, writing, or independent review.
Why use it?
It helps choose the right skill without forcing every task through the same process. It also clarifies how skills for requirements, research, design, writing, and review relate to one another.

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/alieismy/codex-three-layer-delivery/09-task-routing
Clone the repo
git clone --depth 1 https://github.com/alieismy/codex-three-layer-delivery

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 09-task-routing

README.md
[![agentmods](https://agentmods.dev/badge/rules/alieismy/codex-three-layer-delivery/09-task-routing.svg)](https://agentmods.dev/rules/alieismy/codex-three-layer-delivery/09-task-routing)
Your own site
<a href="https://agentmods.dev/rules/alieismy/codex-three-layer-delivery/09-task-routing"><img src="https://agentmods.dev/badge/rules/alieismy/codex-three-layer-delivery/09-task-routing.svg" alt="Measured on agentmods" height="20"></a>
Per session 803 This file is loaded in full into every session.
When invoked 803 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 $0.00803 $0.00803
Opus 5 $0.00402 $0.00402
Sonnet 5 $0.00161 $0.00161
Haiku 4.5 $0.00080 $0.00080

Measured 4d ago against content hash 76ec8a172f43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

09-task-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/project/.cursor/rules/09-task-routing.mdc · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Routing

The eight specialist rd-* research and document skills can be used independently and in any order. They are not a forced pipeline. /rd-delivery is an explicit orchestrator for multi-artifact work, not a mandatory first stage.

Available Skills

Skill Deliverable Daily work
/rd-requirement Structured requirements / PRD / SRS Requirements analysis and product/design input
/rd-feasibility Feasibility study / feasibility analysis report Project feasibility and decision support
/rd-research Evidence package / research notes / fact-check matrix Standards, open source, AI tools, configuration behavior, and contested claims
/rd-solution Technical proposal / high-level design / construction plan System architecture and solution documentation
/rd-design Detailed design document Interface, data, flow, error, security, and concurrency design
/rd-specification Standards/specification draft or clause revision Standards formulation, revision, and normative wording work
/rd-writing Technical article / evidence report / decision brief Audience-ready, source-backed professional writing
/rd-review Independent review findings Engineering documents, research reports, standards, and article review
/rd-delivery Delivery charter / artifact map / phase gates / handoff Explicit multi-stage and cross-session orchestration

Authoring To Review Mapping

Authoring skill Review skill Review mode
/rd-requirement to PRD / SRS /rd-review Requirements Review
/rd-feasibility to feasibility report /rd-review Feasibility Review
/rd-solution to proposal / high-level design / construction plan /rd-review Proposal Review
/rd-design to detailed design /rd-review Design Review
/rd-specification to standard / specification / clause draft /rd-review Standards Review
/rd-writing to technical article / evidence report / decision brief /rd-review Article Review

Read the full file on GitHub · 51 lines

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 · 51 lines · 803 tokens per session scan A 76ec8a172f43

Subscribe to this mod's changes

09-task-routing is a cursor rule published in the GitHub repository alieismy/codex-three-layer-delivery (2 stars, last pushed 4d ago), licensed MIT. It adds 803 tokens to every session, about $0.0040 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.