Semantica is an open-source infrastructure layer that turns enterprise data into structured context and knowledge graphs, where ontologies define meaning and graph reasoning connects facts and decisions. It is intended for AI systems and agents that need traceable, governed, and explainable context in high-stakes domains. The catalogue add-ons provide agent workflows, hooks, and plugins for operating Semantica.
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 semantica-agi/semantica --skill extractgit clone --depth 1 https://github.com/semantica-agi/semanticaWrote 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/semantica-agi/semantica/extract)<a href="https://agentmods.dev/skills/semantica-agi/semantica/extract"><img src="https://agentmods.dev/badge/skills/semantica-agi/semantica/extract/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/semantica-agi/semantica/extract"><img src="https://agentmods.dev/badge/skills/semantica-agi/semantica/extract.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 | $0.00059 | $0.00588 |
| Opus 5.5 | $0.00024 | $0.00235 |
| Sonnet 5.5 | $0.00012 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
extract 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- extract — 86% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/semantica:extract
Run the full extraction pipeline. Usage: /semantica:extract [file_path | "inline text"]
$ARGUMENTS = file path, inline text in quotes, or blank (uses active editor file).
Steps
1. Resolve the source.
- If
$ARGUMENTSis a readable file path →text = open(path).read() - If it's quoted inline text → use directly
- If blank → use the active editor file
2. Clear the result cache to prevent cross-invocation pollution:
from semantica.semantic_extract.cache import extraction_cache
extraction_cache.clear()
3. Run the full pipeline:
from semantica.semantic_extract import (
NamedEntityRecognizer,
RelationExtractor,
EventDetector,
CoreferenceResolver,
TripletExtractor,
ExtractionValidator,
)
# Named Entity Recognition
ner = NamedEntityRecognizer()
entities = ner.extract(text)
# Relation Extraction
rel = RelationExtractor()
relations = rel.extract(text)
# Event Detection
evt = EventDetector()
events = evt.extract(text)
# Coreference Resolution — resolve pronouns/aliases before extraction
coref = CoreferenceResolver()
resolved_text = coref.resolve(text)
# Triplet Extraction (subject–predicate–object)
triplet = TripletExtractor()
triplets = triplet.extract(resolved_text)
# Validate quality
validator = ExtractionValidator()
issues = validator.validate(entities, relations)
4. Report validator warnings above results:
⚠ ExtractionValidator: <warning message>
5. Return results as Markdown tables:
Entities (N total)
| Label | Type | Confidence | Span |
|---|
Relations (M total)
| Source | Relation Type | Target | Confidence |
|---|
Events (K total)
| Label | Type | Participants | Confidence |
|---|
Triplets (J total)
| Subject | Predicate | Object | Confidence |
|---|
6. Summary line:
Extracted: N entities, M relations, K events, J triplets — from <source>
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 Changed de4554e196fb
- 1mo ago First seen · 94 lines · 59 tokens per session scan A 7d99eb08c9b6
extract is a skill published in the GitHub repository semantica-agi/semantica (14,157 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 588 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.