asi: Skill for Claude Code

.claude/skills/wev-hodge-decomp/SKILL.md

wev-hodge-decomp is a skill for Claude Code from plurigrid/asi. It costs 0 tokens per session (2,029 once invoked), scanned A, original, MIT.

A draft mathematical method for separating pairwise market signals into explainable price differences and a remaining cyclic component.

In plain words
What is it for?
Use it to analyze pairwise trading data, estimate the effort needed to remove cyclic discrepancies, and study market structure.
Why use it?
It helps identify market relationships that cannot be explained by assigning one value to each item.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is plurigrid/asi's own configuration. It tells Claude Code how to work on asi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything asi configures →

Reuse

Borrowing it

Nothing to install: this file belongs to plurigrid/asi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/plurigrid/asi/main/.claude/skills/wev-hodge-decomp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/plurigrid/asi

Made for: Claude Code.

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 wev-hodge-decomp

README.md
[![agentmods](https://agentmods.dev/badge/skills/plurigrid/asi/wev-hodge-decomp/github.svg)](https://agentmods.dev/skills/plurigrid/asi/wev-hodge-decomp)
Your own site
<a href="https://agentmods.dev/skills/plurigrid/asi/wev-hodge-decomp"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/wev-hodge-decomp/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.

agentmods 80×15 button for wev-hodge-decomp

Your own site · 80×15
<a href="https://agentmods.dev/skills/plurigrid/asi/wev-hodge-decomp"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/wev-hodge-decomp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,029 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
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 5.1 $0.00000 $0.02029
Opus 5 $0.00000 $0.01014
Sonnet 5 $0.00000 $0.00406
Haiku 4.5 $0.00000 $0.00203

Measured 7d ago against content hash 3386224baa1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wev-hodge-decomp 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 7d 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.

.claude/skills/wev-hodge-decomp/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

World Extractable Value via Pair-Graph Hodge Decomposition

Status: 🧪 Draft — K₃/K₄/K₅ verified Type: Discrete cohomology / optimal transport / market microstructure Principle: WEV = non-exactness of the world, measured in L^p over H₁ Frame: Antisymmetric 1-cochain on pair graph → Hodge splits into coboundary (potential) + harmonic (residue) GF(3)/GF(5): Both required — GF(3) collapses uniform-sign RPS cycles; GF(5) witnesses orientation-H¹


Core Construction

Given pair graph G = (V, E) observed at epoch t with signed 1-cochain α : E → ℝ satisfying α(i,j) = −α(j,i):

  1. Form incidence matrix B : ℝ^|E| × ℝ^|V|, B[e=(u,v), u] = −1, B[e, v] = +1.
  2. Solve normal equations BᵀB φ = Bᵀα (Tikhonov-damped if graph has isolated components). L := BᵀB is the graph Laplacian on vertices.
  3. Decompose α = δφ* + harmonic where δφ*(e=(u,v)) = φ*(v) − φ*(u).
  4. WEV := ‖harmonic‖_p — edge-space p-norm. Common choices:
    • WEV_L¹ = min trade volume to close harmonic under uniform cost per trade.
    • WEV_L² = min trade energy under quadratic price-impact cost.

The coboundary part δφ* is explained by a vertex potential φ* — this is the Kantorovich dual / "type price" / clearing prices. The harmonic part is what no potential can explain — the extractable residue.


5-Instance Unification

Antisymmetric α required. Semantics splits into extractive (closure = transaction) vs diagnostic (observational):

Layer Vertex α (edge signal) WEV semantics
RPS / games agent regret-sign gap-to-Nash
Hough MM harness trader / MM PnL-asymmetry arb budget [extractive]
MEV tx ordering-regret MEV bound [extractive]
Wardrop / Braess road segment travel-time-Δ Braess cost [extractive]
MAC RF observer device sgn(RSSI_i − RSSI_j) flock evidence [diagnostic]
Passport sybil address sgn(first_stamp_t_i − t_j) under scorer C sybil evidence [diagnostic]
Face-patch fMRI patch partial-correlation precedence under stimulus prosopagnosia index [diagnostic]

Read the full file on GitHub · 126 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. 7d ago First seen · 126 lines · 0 tokens per session scan A 3386224baa1f

Subscribe to this mod's changes

wev-hodge-decomp is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,029 tokens. 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