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 jamiemill/layers-skills --skill layers-orientgit clone --depth 1 https://github.com/jamiemill/layers-skillsWrote 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/jamiemill/layers-skills/layers-orient)<a href="https://agentmods.dev/skills/jamiemill/layers-skills/layers-orient"><img src="https://agentmods.dev/badge/skills/jamiemill/layers-skills/layers-orient/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/jamiemill/layers-skills/layers-orient"><img src="https://agentmods.dev/badge/skills/jamiemill/layers-skills/layers-orient.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00021 | $0.00996 |
| Opus 5 | $0.00010 | $0.00498 |
| Sonnet 5 | $0.00004 | $0.00199 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
layers-orient 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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/layers-orient
Assumes /layers-intro has been loaded for framework context.
Orient is a rapid diagnostic — the front door for finding the live decisions the other skills then work. It maps the current state of decisions across all seven layers, identifies the bottleneck — the lowest layer with unresolved or risky decisions — and recommends where to focus next.
It is not a deep dive into any layer. That's what the individual layer skills are for. Orient answers the prior question: which layer deserves attention most urgently? Keep it fast and light — the output is a short audit and one recommendation, not a report.
What it assesses:
- Whether key decisions have been made at each layer, and how solidly
- Whether decisions treated as solid are actually assumptions
- Which layer is the most foundational with unresolved work, creating risk for everything above
Quality signals — when orient is done well:
- The bottleneck layer is specifically named, not vaguely gestured at
- Assumed layers are distinguished from Strong ones — they require different responses
- The recommendation connects to a specific skill with a clear reason
Guided session
Describe your design situation and what prompted you to pick it up, or say "let's orient" to start.
(Capture is opt-in and light — see /layers-intro. For orient, the audit table itself is usually all that's worth keeping.)
Then ask:
- What product or feature are you working on?
- What design challenge are you facing right now?
- How far along is this work — early exploration, active design, or fixing something in an existing product?
Listen for clues about which layers have already been worked through and which are thin or missing.
Layer audit
Work through each layer with one or two targeted questions. Rate each as: Strong / Partial / Assumed / Weak / Not started / N/A
Observed behaviour "What user research do you have? Have you spoken to users, observed them, or have analytics? Or is this mostly based on what the team believes users do?"
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.
- 9d ago First seen · 109 lines · 21 tokens per session scan A cdd02877ee65
layers-orient is a skill published in the GitHub repository jamiemill/layers-skills (299 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 996 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…