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 skills add alieismy/codex-three-layer-delivery --skill rd-solutiongit 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/skills/alieismy/codex-three-layer-delivery/rd-solution)<a href="https://agentmods.dev/skills/alieismy/codex-three-layer-delivery/rd-solution"><img src="https://agentmods.dev/badge/skills/alieismy/codex-three-layer-delivery/rd-solution/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/skills/alieismy/codex-three-layer-delivery/rd-solution"><img src="https://agentmods.dev/badge/skills/alieismy/codex-three-layer-delivery/rd-solution.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 | $0.00079 | $0.01823 |
| Opus 5.5 | $0.00032 | $0.00729 |
| Sonnet 5.5 | $0.00016 | $0.00365 |
| Haiku 4.5 | $0.00008 | $0.00182 |
Grade A, and why
rd-solution 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 20d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rd-solution
Produce decision-ready technical proposals, high-level designs, solution architecture documents, and construction plans.
Deliverables
- Technical proposal / High-level design / Solution architecture document
- Construction plan or design-oriented project plan
- Candidate solution comparison matrix
- Recommended solution with risk statement
- Architecture decision record inputs for material choices
Execution Steps
1. Objective & Constraint Confirmation
- Clarify the document type (technical proposal / high-level design / solution architecture / construction plan)
- Confirm the audience (decision-makers / technical team / client reviewers)
- Confirm constraints: timeline, budget, tech stack, compliance requirements
- Separate approved constraints from current practices or candidate assumptions that may be changed within the requested design space
- When validation or adoption is in scope, identify its decision stage: exploration, bounded pilot, wider adoption, or production commitment. Distinguish the target architecture, next recommended step, and immediate authorized scope
- Check for existing requirements documents (
rd-requirementoutput) - Check for feasibility inputs (
rd-feasibilityoutput) when the project has an approval phase - Resolve discoverable facts from project artifacts; ask the user only for material decisions that remain open
- Use established domain terminology and surface conflicts instead of silently creating synonyms
Completion criterion: the target document, audience, approved inputs, constraints, material decision stage, open decisions, and terminology basis are explicit enough to generate real alternatives; validation or adoption scope is not confused with the target architecture or execution authority.
2. Solution Research & Candidate Generation
- Generate at least 2 candidate solutions when a real architectural or technical choice exists
- Where there is meaningful design space, seek a materially different approach with a credible benefit mechanism, including emerging technology or a new workflow when relevant. Mark untested benefits as hypotheses and judge novelty by fit and value; retain only justified alternatives
- Each solution should include: architecture overview, core components, data/interface boundaries, technology choices, deployment or operating assumptions
- Identify decision-material maturity, compatibility, policy, cost, or current-version evidence gaps and apply Tool Selection below; do not turn candidate generation into an unbounded search phase
- For infrastructure, networking, proxy, VPN, VPS, or AI-tool solutions, model trust boundaries, control/data flows, credential ownership, platform/version constraints, observability, recovery, and exit path
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 20d ago Changed a86362e90bf6
- 24d ago Changed · +6 lines d4e4ecd8bb7e
- 1mo ago Changed 0e61abac9675
- 2mo ago First seen · 157 lines · 79 tokens per session scan A 3a1044d0549f
rd-solution is a skill published in the GitHub repository alieismy/codex-three-layer-delivery (12 stars, last pushed 17d ago), licensed MIT. It adds 79 tokens to every session and 1,823 once invoked, about $0.0003 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…