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 plurigrid/asi --skill three-matchgit clone --depth 1 https://github.com/plurigrid/asiWrote 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/plurigrid/asi/three-match)<a href="https://agentmods.dev/skills/plurigrid/asi/three-match"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/three-match/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/plurigrid/asi/three-match"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/three-match.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 | $0.00027 | $0.01443 |
| Opus 5.5 | $0.00011 | $0.00577 |
| Sonnet 5.5 | $0.00005 | $0.00289 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
three-match 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 1mo 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three-Match Skill: 3-SAT via Colored Subgraph Isomorphism
Status: ✅ Production Ready Trit: -1 (MINUS - conservative/geodesic) Principle: Local constraints → Global correctness Frame: Non-backtracking geodesics with Möbius filtering
Overview
Three-Match reduces 3-SAT to 3-coloring which reduces to colored subgraph isomorphism. The 3-MATCH gadget enforces constraints LOCALLY via:
- Non-backtracking geodesics (prime paths, μ(n) ≠ 0)
- Möbius inversion filtering (back-and-forth cancellation)
- GF(3) conservation (sum ≡ 0 mod 3)
Correct by construction: If local geodesic constraints are satisfied, global 3-SAT solution is guaranteed.
Core Formula
# Three colors match at depth d iff:
# - Pairwise differences have 3-adic valuation ≥ d
# - No backtracking (each color unique in path)
# - GF(3) sum ≡ 0 (mod 3)
v₃(|a - b|) ≥ d ∧ v₃(|b - c|) ≥ d ∧ v₃(|c - a|) ≥ d
Why Non-Backtracking?
- Prime paths: μ(n) ≠ 0 ⟺ n is squarefree
- No revisiting: Each state appears once in geodesic
- Möbius filtering: Composites (backtracking) cancel out
- Spectral gap: Ramanujan property (λ₂ ≤ 2√(k-1))
Gadgets
1. ThreeMatch Gadget
Three colors forming a valid local constraint:
match = ThreeMatchGeodesicGadget::ThreeMatch.new(seed: 0x42D, depth: 1)
match.color_a # => { trit: -1, hex: "#2626D8", polarity: :minus }
match.color_b # => { trit: 0, hex: "#26D826", polarity: :ergodic }
match.color_c # => { trit: 1, hex: "#D82626", polarity: :plus }
match.gf3_conserved? # => true
2. NonBacktrackingGeodesic
Prime path through color space:
geo = NonBacktrackingGeodesic.new(seed: seed, length: 8).generate!
geo.prime? # => true (no backtracking)
geo.moebius_product # => ±1 (non-zero for primes)
geo.moebius_filter # => filtered path (only primes kept)
3. ColoredSubgraphGadget
3-SAT clause reduction:
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.
- 1mo ago First seen · 188 lines · 27 tokens per session scan A 910396cf543d
three-match is a skill published in the GitHub repository plurigrid/asi (70 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 1,443 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 2026-09-03.
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…