Borrowing it
Nothing to install: this file belongs to GabrielOnDelphi/Claude-Tools-for-Delphi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GabrielOnDelphi/Claude-Tools-for-Delphi/main/.claude/skills/light-new-Align/SKILL.mdgit clone --depth 1 https://github.com/GabrielOnDelphi/Claude-Tools-for-DelphiWrote 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/gabrielondelphi/claude-tools-for-delphi/light-new-align)<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-new-align"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-new-align/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/gabrielondelphi/claude-tools-for-delphi/light-new-align"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-new-align.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 | $0.00056 | $0.01302 |
| Opus 5 | $0.00028 | $0.00651 |
| Sonnet 5 | $0.00011 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
light-new-Align 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 6d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/light-new-Align — Align on the design before building
Reach a shared design concept with the user before producing any plan, PRD, or code. Get there by interviewing — one question at a time, each carrying your own recommended answer — and by skipping every question you can answer yourself.
Why: the expensive failure mode is the AI confidently building the wrong thing. A short, high-stakes interview surfaces the irreversible Delphi decisions (binary-compatibility, the LightSaber boundary, persistence) while they are still cheap to change.
How to run it
- Read the brief the user gives (or the conversation). Read the project
CLAUDE.mdand scan the code enough to know what already exists — use the Explore agent if more than ~3 lookups would be needed, rather than reading widely into this context. Do not ask anythingCLAUDE.md, the brief, or the code already answers. - Ask one question at a time, each with your recommended answer, highest-stakes first. Wait for the reply before the next question. Never bundle several questions into one. Never accept silent agreement — if the user just says "yes", restate what they agreed to.
- Continue until the questions stop revealing new decisions, or you hit the adaptive cap (below) — then pause and ask whether to continue or proceed.
- End by printing the auto-decided list (everything you settled yourself, so the user can veto any item) and a 3–5 line shared-concept summary, then the line: "Aligned — ready to proceed?" Do NOT start the plan / PRD / code yourself; hand back to whatever comes next.
Skip what you can answer yourself
If the recommended answer is obvious from CLAUDE.md, the brief, the codebase scan, or established Delphi practice, do not ask — record it in the running auto-decided list and show that list at the end. Only ask where your confidence is genuinely below ~80%, OR where the decision is irreversible enough that the user must confirm it explicitly (binary-compatibility, persistence format, public-API shape). The interview's value is in the few questions that actually matter — not in volume.
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.
- 6d ago Changed · +2 lines 0ea12c5a9b9a
- 10d ago First seen · 69 lines · 56 tokens per session scan A 5011b407a341
light-new-Align is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (17 stars, last pushed 3d ago), licensed MPL-2.0. It adds 56 tokens to every session and 1,302 once invoked, about $0.0003 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…