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.
npx agentmods add rules/alieismy/codex-three-layer-delivery/09-task-routinggit clone --depth 1 https://github.com/alieismy/codex-three-layer-deliveryWrote 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/alieismy/codex-three-layer-delivery/09-task-routing)<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>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 | $0.00803 | $0.00803 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
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.
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 |
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.
- 4d ago First seen · 51 lines · 803 tokens per session scan A 76ec8a172f43
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.
Other cursor rules, from other repositories
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.
cli-error-handling
CLI command error handling patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.