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-deliverygit 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-delivery)<a href="https://agentmods.dev/skills/alieismy/codex-three-layer-delivery/rd-delivery"><img src="https://agentmods.dev/badge/skills/alieismy/codex-three-layer-delivery/rd-delivery/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-delivery"><img src="https://agentmods.dev/badge/skills/alieismy/codex-three-layer-delivery/rd-delivery.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 | $0.00067 | $0.02142 |
| Opus 5.5 | $0.00027 | $0.00857 |
| Sonnet 5.5 | $0.00013 | $0.00428 |
| Haiku 4.5 | $0.00007 | $0.00214 |
Grade A, and why
rd-delivery 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rd-delivery
Coordinate a bounded document-delivery engagement without replacing the specialist rd-* Skills that produce or review each artifact.
Deliverables
- Delivery charter or task capsule
- Artifact, dependency, and decision map
- Phase plan with entry and exit gates
- Status and verification record
- Cross-session or cross-agent handoff
For a durable engagement record, read delivery-record.md. Use the repository's existing location and naming conventions; do not impose a new task directory or framework when none is needed.
Operating Rules
- Use this Skill only when the request explicitly asks for multi-stage or multi-document orchestration, phase gates, or a durable cross-session handoff. The request need not name the Skill, but task complexity or multiple outputs alone do not qualify; route a single deliverable directly to its specialist Skill
- Select only the stages required by the decision and deliverables; never force all
rd-*Skills into a pipeline - Treat identified, current authoritative project artifacts as sources of truth and chat as transient working context
- Keep authority explicit: an agent may draft, verify, or recommend, but only an authorized stakeholder can approve or baseline an artifact
- Identify the smallest relevant context set for each stage. At phase boundaries, confirm authoritative inputs and applicable scope remain current; reuse inspected unchanged context and load only changed, newly applicable, or decision-critical material whose validity is uncertain
- Keep durable artifact classes distinct: long-lived need and intent, current-state architecture, engagement-specific change design, decision rationale, evidence, and review findings must not silently substitute for one another
- Treat the delivery record as an index, not a second copy of its artifacts: keep status and concise decision context in the record, and link to the one authoritative location for full content
- Keep the current project stage or responsibility, primary outcome, and shortest evidence path explicit; allocate work to that outcome before optional supporting improvements
- Reuse applicable existing gates. Add generalized validators, broad test matrices, security-hardening tracks, or frameworks only when required by the approved scope, an observed reproducible failure, an authoritative requirement, or a material risk; otherwise keep them out of the active frontier with a re-entry condition
What ships with it
6 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 · -2 lines · -17 tokens per session cd887c5f8ac8
- 27d ago Changed · -1 lines 60be0714e9fb
- 1mo ago Changed · +9 lines 84fec81e361c
- 2mo ago First seen · 132 lines · 84 tokens per session scan A 702277aa6875
rd-delivery is a skill published in the GitHub repository alieismy/codex-three-layer-delivery (12 stars, last pushed 17d ago), licensed MIT. It adds 67 tokens to every session and 2,142 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…