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 8b-is/smart-tree --skill manybody-strang-mem8git clone --depth 1 https://github.com/8b-is/smart-treeWrote 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/8b-is/smart-tree/manybody-strang-mem8)<a href="https://agentmods.dev/skills/8b-is/smart-tree/manybody-strang-mem8"><img src="https://agentmods.dev/badge/skills/8b-is/smart-tree/manybody-strang-mem8/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/8b-is/smart-tree/manybody-strang-mem8"><img src="https://agentmods.dev/badge/skills/8b-is/smart-tree/manybody-strang-mem8.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00081 | $0.00891 |
| Opus 5.5 | $0.00032 | $0.00356 |
| Sonnet 5.5 | $0.00016 | $0.00178 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
manybody-strang-mem8 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 2d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quantum Many-Body Kohn–Sham DFT & Strang Wave Engine (smart-tree v10.10.0+)
manybody-strang-mem8 (src/mem8/regularity/salience_karp_manybody.rs) bridges quantum computational chemistry and MEM8 wave dynamics to model $N$-symbol codebases without hitting the exponential $O(2^N)$ many-body wave-function wall.
1. Kohn–Sham DFT Super-Orbitals & Local Natural Orbital (T8R) Correlations
In quantum chemistry, storing an exact $N$-electron wave function $\Psi(\mathbf{r}_1, \dots, \mathbf{r}_N)$ scales as $O(2^N)$. Kohn–Sham Density Functional Theory (DFT) and Linear-Scaling CCSD(T) (Local Natural Orbitals / QM-MM) break this curse of dimensionality by separating the mean-field one-particle density $\rho(\mathbf{r})$ from localized strong correlations:
| Quantum Many-Body Concept | smart-tree MEM8 Equivalent |
Complexity Reduction |
|---|---|---|
| One-Particle Kohn–Sham Density $\rho(\mathbf{r})$ | SuperNodeCentroidPod ([f32; 64] L2-normalized wave centroid per Szemerédi cluster $V_i$) |
$N$ symbols $\rightarrow K \ll N$ orbitals |
| Hartree–Fock / Exchange Integrals $\langle \psi_i \vert \hat{V}_{\text{XC}} \vert \psi_j \rangle$ | RegularSuperEdgePod density $d_p(V_i, V_j) \times$ felix_dot64_f32 SIMD wave overlap |
$O(N^2) \rightarrow O(K^2)$ |
| Local Natural Orbitals (LNO) / QM-MM Active Space | T8R LEB128 Exception Ledger (OutlierVertex, IrregularPair, ArchitecturalLeak) |
Exact $O(\vert E_{\text{T8R}}\vert)$ local correlation |
2. Second-Order Strang Split-Operator Salience Wave Propagation
Because the observable temporal drift operator $A_{\text{temporal}}$ ($d_T$ decay) and the relational Kohn–Sham coupling operator $B_{\text{relational}}$ ($d_R$ super-edge + T8R wave exchange) do not commute ($[A, B] \neq 0$), smart-tree evolves the $K$-orbital salience state $\Psi(t)$ via Second-Order Strang Operator Splitting:
$$\Psi(t + h) = e^{\frac{h}{2} A_{\text{temporal}}} , e^{h B_{\text{relational}}} , e^{\frac{h}{2} A_{\text{temporal}}} \Psi(t) + O(h^3)$$
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.
- 2d ago First seen · 43 lines · 81 tokens per session scan A 9522b512254e
manybody-strang-mem8 is a skill published in the GitHub repository 8b-is/smart-tree (272 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 891 once invoked, about $0.0003 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 2026-11-04.
manybody-strang-mem8 compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| manybody-strang-mem88b-is/smart-tree | Skill | 272 | yesterday | MIT | A | 81 | Claude Code, Codex |
| project-wikiGeminiLight/MindOS | Skill | 704 | 14d ago | MIT | A | 63 | Claude Code, Codex |
| mindos-zhGeminiLight/MindOS | Skill | 704 | 14d ago | MIT | A | 490 | Claude Code |
| mindosGeminiLight/MindOS | Skill | 704 | 14d ago | MIT | A | 136 | Claude Code |
| mindos-maxGeminiLight/MindOS | Skill | 704 | 14d ago | MIT | A | 145 | Claude Code |
| mindos-viewsGeminiLight/MindOS | Skill | 704 | 14d ago | MIT | A | 60 | Claude Code, Codex |
| mindosGeminiLight/MindOS | Skill | 704 | 14d ago | MIT | A | 157 | Claude Code, Codex |