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 flyxion-salience-ontologygit 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/flyxion-salience-ontology)<a href="https://agentmods.dev/skills/8b-is/smart-tree/flyxion-salience-ontology"><img src="https://agentmods.dev/badge/skills/8b-is/smart-tree/flyxion-salience-ontology/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/flyxion-salience-ontology"><img src="https://agentmods.dev/badge/skills/8b-is/smart-tree/flyxion-salience-ontology.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 | $0.00103 | $0.00893 |
| Opus 5.5 | $0.00041 | $0.00357 |
| Sonnet 5.5 | $0.00021 | $0.00179 |
| Haiku 4.5 | $0.00010 | $0.00089 |
Grade A, and why
flyxion-salience-ontology 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flyxion Salience Ontology — $d_T(x, q) \neq d_R(x, q)$ (smart-tree v10.10.0+)
"Retained does not imply retrievable; retrievable does not imply salient." $$\text{retained}(x) \not\Rightarrow \text{retrievable}(x, q) \not\Rightarrow \text{salient}(x, q)$$
flyxion-salience-ontology operationalizes Flyxion's Recency as Salience (2026) inside smart-tree (src/mem8/regularity/salience_karp_manybody.rs). It prevents chronological retrieval-as-amnesia when AI agents (agy, opencode, crush, claude) inspect a repository.
1. Core Mathematical Separation: $d_T(x, q)$ vs. $d_R(x, q)$
Every codebase query $q$ at time $t_q$ induces two distinct metrics over artifacts $x \in \mathcal{D}$:
- Observable Temporal Distance ($d_T$):
$$d_T(x, q) = t_q - t_a(x), \quad r_T(x) \in {0, \dots, N-1}$$
Easy to sort on (
mtime/ last activity), so naive retrieval engines promote $d_T$ from a cheap prefix/handshape filter into a global salience ranking. - Latent Relational Distance ($d_R$):
$$d_R(x, q) = 0.7 \cdot d_{\text{Steiner}}!\left(\text{cluster}(x), \mathcal{T}_q\right) + 0.3 \cdot \frac{1}{1 + \ln(1 + \deg(x))}$$
Measures structural geodesic resistance distance on the Szemerédi + Voronoi Steiner backbone (
erdos_steiner.rs) and Erdős Center $Z(G)$ membership.
Proxy Disagreement & "Corrugated Iron" Rescue
- Proxy Disagreement Probability: $\Pr[x^_T \neq x^_R]$ across the top-$k$ retrieval frontier.
- "Load-Bearing Old" ("Corrugated Iron") Artifacts (
LoadBearingOldArtifact): Foundational files where $r_T(x) \gg r_R(x)$ — old modification timestamps that chronological feeds bury, even though they sit at Erdős Number0or1on the active Steiner backbone.
2. CLI & Agent Workflow
# Inspect Flyxion Salience Ontology, Proxy Disagreement & Rescued Load-Bearing Old Files:
st --erdos-center .
# Full 8-Pillar JSON Diagnostic (includes `flyxion_salience_ontology`):
st --mode the-book .
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 · 48 lines · 103 tokens per session scan A 70efe8b83e40
flyxion-salience-ontology is a skill published in the GitHub repository 8b-is/smart-tree (272 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 893 once invoked, about $0.0004 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.
flyxion-salience-ontology compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flyxion-salience-ontology8b-is/smart-tree | Skill | 272 | yesterday | MIT | A | 103 | 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 |