möbius-path-filtering

möbius-path-filtering is a skill for Claude Code, Codex from plurigrid/asi. It costs 21 tokens per session (1,817 once invoked), scanned A, original, MIT.

A path-filtering method for nested data that rejects ambiguous paths which revisit or refer to the same logical position in conflicting ways. It checks these paths before they are compiled or cached.

In plain words
What is it for?
Use it when validating navigation or transformation paths through nested dictionaries, lists, or similar structures.
Why use it?
Complex nested structures can contain repeated keys or overlapping selections, making a requested transformation unclear. This prevents such invalid paths from being reused.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/plurigrid/asi/mobius-path-filtering
Any agent
npx skills add plurigrid/asi --skill mobius-path-filtering
Clone the repo
git clone --depth 1 https://github.com/plurigrid/asi

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for möbius-path-filtering

README.md
[![agentmods](https://agentmods.dev/badge/skills/plurigrid/asi/mobius-path-filtering.svg)](https://agentmods.dev/skills/plurigrid/asi/mobius-path-filtering)
Your own site
<a href="https://agentmods.dev/skills/plurigrid/asi/mobius-path-filtering"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/mobius-path-filtering.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,817 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.01817
Opus 5 $0.00010 $0.00908
Sonnet 5 $0.00004 $0.00363
Haiku 4.5 $0.00002 $0.00182

Measured 3d ago against content hash 1031bae29d00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

möbius-path-filtering 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 3d 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.

ies/music-topos/.agents/skills/möbius-path-filtering/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Möbius Path Filtering

Core Concept

A Möbius filter is a non-orientable topological constraint that eliminates paths where traversal would require "doubling back" or revisiting a configuration from a different orientation.

In navigator terms: some paths appear valid locally but are invalid globally because they would require the navigator to traverse the same logical position in two different ways simultaneously—geometrically impossible on a Möbius surface.

This constraint is checked before path compilation, preventing invalid Navigators from ever being cached.

Why Möbius Filtering?

The Problem

Consider a nested structure:

data = Dict(
  "a" => [1, 2, 3],
  "b" => Dict(
    "c" => [4, 5, 6],
    "a" => [7, 8, 9]  # Same key name, different context!
  )
)

A naive path like [ALL_KEYS, ALL_VALUES, ALL] might:

  1. Navigate to key "a" → [1, 2, 3]
  2. Navigate to key "b" → {...}
  3. Navigate to nested "a" → [7, 8, 9]

But what if we then try to transform all "a" keys? The path becomes ambiguous:

  • Is "a" referring to the top-level key or the nested key?
  • Can we transform both simultaneously?
  • What if the nested "a" contains a reference back to the top-level "a"?

On a Möbius surface, this ambiguity is geometrically impossible—you can't have two distinct orientations of the same location.

The Solution

Möbius filtering rejects paths that would create "twists" in the navigation space. It asks:

"Does this path require the navigator to visit the same logical location from two different orientations?"

If yes → path is invalid and compilation is rejected.

Architecture

Möbius Invariant

For each path step, track:

  1. Position - current location in structure
  2. Orientation - the "direction" we're approaching from (forward/reverse)

A valid path maintains consistent orientation throughout:

  • Cannot visit (position, orientation) pairs in contradictory ways
  • Cannot have cycles where orientation flips

Read the full file on GitHub · 227 lines

Changes

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.

  1. 3d ago First seen · 227 lines · 21 tokens per session scan A 1031bae29d00

Subscribe to this mod's changes

möbius-path-filtering is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,817 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 2026-09-01.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens