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 causalgit 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/causal)<a href="https://agentmods.dev/skills/semantica-agi/semantica/causal"><img src="https://agentmods.dev/badge/skills/semantica-agi/semantica/causal/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/causal"><img src="https://agentmods.dev/badge/skills/semantica-agi/semantica/causal.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 | $0.00031 | $0.00479 |
| Opus 5.5 | $0.00012 | $0.00192 |
| Sonnet 5.5 | $0.00006 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
causal 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.
What it actually says
/semantica:causal
Analyze causal relationships and infer impacts. Usage: /semantica:causal <task> [args]
$ARGUMENTS = task + optional target entity, filter, or intervention.
chain [--subject <node>] [--depth N]
Build and inspect causal chains for a subject or category.
from semantica.context.causal_analyzer import CausalChainAnalyzer
from semantica.context import AgentContext
# Option 1: Use an existing AgentContext decision backend
chain = ctx.get_causal_chain(
decision_id=decision_id,
direction="upstream",
max_depth=depth,
)
# Option 2: Use CausalChainAnalyzer directly
analyzer = CausalChainAnalyzer(graph_store=ctx.knowledge_graph)
downstream = analyzer.get_causal_chain(
decision_id=decision_id,
direction="downstream",
max_depth=depth,
)
Output: chain steps, cause strength, effect reach, and summary graph.
intervene <node> <action> [--scenario <json>]
Analyze decision impact and influenced decisions (current causal API).
analyzer = CausalChainAnalyzer(graph_store=ctx.knowledge_graph)
impact_score = analyzer.get_causal_impact_score(decision_id=decision_id)
influenced = analyzer.get_influenced_decisions(
decision_id=decision_id,
max_depth=depth,
)
Return: impact score, influenced decisions, and downstream scope.
counterfactual <fact> [--weight N]
Trace root causes and temporal causal paths.
analyzer = CausalChainAnalyzer(graph_store=ctx.knowledge_graph)
roots = analyzer.find_root_causes(decision_id=decision_id, max_depth=depth)
historical_chain = analyzer.trace_at_time(
event_id=decision_id,
at_time="2026-01-01T00:00:00Z",
direction="upstream",
max_depth=depth,
)
Output: root decision lineage and time-bounded causal context.
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 · 75 lines · 31 tokens per session scan A cc5ac111d0f7
causal is a skill published in the GitHub repository semantica-agi/semantica (14,221 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 479 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 2026-08-30.
Other skills, from other repositories
scienceworld-measurement-taker
Use when the agent needs to measure a quantitative property (temperature, weight, pH) of a target object or substance using a measurement tool. This skill covers acquiring the tool, preparing both tool and target with focus actions, executing the measurement via "use [TOOL] on [TARGET]", and interpreting the resulting…
scienceworld-animal-identifier
Use when the agent needs to locate, identify, and focus on a specific animal or biological entity in the ScienceWorld environment. This skill handles tasks involving animal comparison, examination, or interaction (such as determining lifespan extremes) by navigating to the correct location with "teleport to"…
scienceworld-inventory-focus
Use when the agent needs to confirm and prepare a specific inventory item before using it in an experiment or task step. This "focus on [ITEM] in inventory" action verifies the correct item has been collected and signals intent, ensuring operational readiness for subsequent actions like measurement, combination, or…
scienceworld-object-selector
Use when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical component, container), properties, or category. This skill surveys visible objects with "look around", evaluates each against the task requirements…
scienceworld-task-focuser
Use when the agent needs to direct attention to a specific object in the environment or inventory before performing a critical action such as measuring, using, or connecting. This preparatory "focus on" step signals intent to the ScienceWorld system, often unlocking required state changes for subsequent interactive…
scienceworld-tool-validator
Use when the agent has acquired a tool or instrument and needs to verify it is operational before first use in a critical task step. This skill performs a lightweight pre-use check via "focus on [TOOL] in inventory" and confirms readiness based on the system's response, ensuring the tool is functional before…