Magnitude is an open-source inference server, meaning software that runs language models and answers requests on a user's own computer. It profiles available hardware, recommends suitable local models, and connects them to coding agents for private and offline use on macOS, Linux, or Windows through WSL. Its catalogue entries help agents set up and use Magnitude.
Borrowing it
Nothing to install: this file belongs to magnitudedev/magnitude. 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/magnitudedev/magnitude/main/.agents/skills/formulate-abstractions/SKILL.mdgit clone --depth 1 https://github.com/magnitudedev/magnitudeWrote 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/magnitudedev/magnitude/formulate-abstractions)<a href="https://agentmods.dev/skills/magnitudedev/magnitude/formulate-abstractions"><img src="https://agentmods.dev/badge/skills/magnitudedev/magnitude/formulate-abstractions/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/magnitudedev/magnitude/formulate-abstractions"><img src="https://agentmods.dev/badge/skills/magnitudedev/magnitude/formulate-abstractions.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 | $0.00058 | $0.00615 |
| Opus 5 | $0.00029 | $0.00308 |
| Sonnet 5 | $0.00012 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
formulate-abstractions 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 12d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Formulate the broad semantic shapes of a system before designing their implementation. Use this process either within a design conversation or while creating or revising an existing plan; adapt the depth and presentation to the surrounding task.
Phase 1: Reset the frame
Bracket the current implementation and any terminology or structure it suggests. Preserve genuine requirements and constraints, but do not treat existing code, plans, or names as the natural shape of the problem.
Start from what the system must mean and do.
Phase 2: Formulate the broad shapes
Identify:
- Core behaviors and guarantees
- Semantic entities and precise terminology
- Responsibilities and boundaries
- Relationships, ownership, and information flow
- The smallest high-level architecture that makes these concepts coherent
Prefer one meaningful concept over several overlapping ones. Avoid abstractions that merely rename implementation details, introduce indirection, or anticipate cases without evidence.
Present the proposal at the semantic level first: terminology, behavior, boundaries, and broad architecture. Keep it concise, high-signal, and easy to scan. Do not descend into files, APIs, schemas, classes, or migration details yet.
Phase 3: Align with the user
Surface ambiguity only when it affects the broad shapes or represents a meaningful product or architectural choice. State the proposed interpretation and its consequences so the user can respond to a concrete model rather than an open-ended question.
When the user appears to want a design conversation, pause at natural decision points and offer a compact proposal for feedback. Resolve questions that can be answered through reasoning or research autonomously; reserve user attention for key semantic decisions.
Treat agreement as provisional when important evidence remains unexplored.
Phase 4: Ground and challenge
Once the broad shapes are sufficiently aligned, investigate the relevant code, design documents, plans, constraints, and adjacent systems. Work from the proposal into progressively specific aspects, using research to:
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.
- 12d ago First seen · 55 lines · 58 tokens per session scan A 813ba9fc36f4
formulate-abstractions is a skill published in the GitHub repository magnitudedev/magnitude (4,347 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 615 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…
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…