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 lexler/skill-factory --skill aligngit clone --depth 1 https://github.com/lexler/skill-factoryWrote 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/lexler/skill-factory/align)<a href="https://agentmods.dev/skills/lexler/skill-factory/align"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/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/lexler/skill-factory/align"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/align.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00025 | $0.00569 |
| Opus 5.5 | $0.00010 | $0.00228 |
| Sonnet 5.5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
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 15d 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.
STARTER_CHARACTER = 🎯
Goal
Align your mental model with the user's before implementation begins. Divergence found during implementation is expensive, so surface it now while changes are free.
Think first, then propose the approach. It's easier to complain than to explain: a user looking at a concrete, scannable proposal spots what's wrong early and corrects you before you build the wrong thing.
Language
Write the shortest message that is clear on the first read, using plain English words and complete sentences.
Flow: zoom in
Start from high level and go lower. Zoom in one level at a time:
Goal → Big Picture → Straightforward Details → Non-obvious Decisions (one by one)
1. Goal
State what you understand the goal to be and why it matters. Keep it to a sentence or two. This catches the deepest misalignment, because if you're solving the wrong problem, nothing else matters.
Confirm with the user that the goal is right before moving on.
2. Big picture
Present the overall shape of the approach: how do the pieces relate, what's the high-level flow. Use an ASCII diagram and a few sentences.
Confirm with the user before going deeper.
3. Straightforward details
Decisions where there's only one reasonable approach.
Group decisions where there's commonality that helps understand. Organize the group around meaningful differences.
Include specific details when they change what the user is agreeing to, otherwise stay on higher level.
Use short prose or bullets for simple choices. Use an ASCII diagram when seeing a relationship, structure, or flow makes the choice clearer.
Describe the resulting behavior with complete statements.
4. Non-obvious decisions
Decisions with real tradeoffs, multiple valid approaches, or where your recommendation might surprise the user.
First, present a brief index of what's coming, staying on high level: the problem titles only, without recommendations. This lets the user see the scope.
Then walk through each one (or small related groups) with:
- The problem: what is being decided, why it matters
- ⭐ Recommended approach with rationale
- ❌ Alternatives considered with why they were rejected
- ASCII diagram if the item involves structure or flow
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.
- 15d ago Changed · -3 lines · -8 tokens per session c7d4ff72936c
- 1mo ago First seen · 74 lines · 33 tokens per session scan A 789a4a30ac30
align is a skill published in the GitHub repository lexler/skill-factory (239 stars, last pushed 16d ago), licensed Apache-2.0. It adds 25 tokens to every session and 569 once invoked, about $0.0001 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 2026-08-30.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.