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 validategit 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/validate)<a href="https://agentmods.dev/skills/semantica-agi/semantica/validate"><img src="https://agentmods.dev/badge/skills/semantica-agi/semantica/validate/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/validate"><img src="https://agentmods.dev/badge/skills/semantica-agi/semantica/validate.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 | $0.00000 | $0.01140 |
| Opus 5 | $0.00000 | $0.00570 |
| Sonnet 5 | $0.00000 | $0.00228 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
validate 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 9d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/semantica:validate
Validate pipeline and graph quality. Usage: /semantica:validate <target> [options]
$ARGUMENTS = target type + optional config or path.
pipeline [--config '<json>']
Validate a full pipeline builder configuration.
from semantica.pipeline.pipeline_builder import PipelineBuilder
from semantica.pipeline.pipeline_validator import PipelineValidator
builder = PipelineBuilder()
if config_json:
import json
builder.build_pipeline(json.loads(config_json))
# PipelineBuilder has its own quick validate
quick = builder.validate_pipeline() # returns Dict
# PipelineValidator gives full ValidationResult(valid, errors, warnings)
# Does NOT raise — always returns a result object
validator = PipelineValidator()
result = validator.validate(builder)
# Also check inter-step dependencies
deps = validator.check_dependencies(builder)
Output:
Pipeline Validation: VALID ✓ | INVALID ✗
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Steps: N registered
Valid: M steps
Errors (K):
✗ [step_name] <error message>
Warnings (J):
⚠ [step_name] <warning message>
Dependencies:
✓ All dependencies resolved
✗ Step "<name>" depends on missing step "<dep>"
Result: <valid> — K errors, J warnings
step <step_name> [--type <type>] [--constraints '<json>']
Validate a single pipeline step.
from semantica.pipeline.pipeline_builder import PipelineBuilder
from semantica.pipeline.pipeline_validator import PipelineValidator
import json
builder = PipelineBuilder()
step = builder.get_step(step_name)
validator = PipelineValidator()
result = validator.validate_step(
step=step,
**json.loads(constraints_json) if constraints_json else {},
)
Output: same checklist format but scoped to a single step.
dependencies
Check all inter-step dependency resolution for the active pipeline.
from semantica.pipeline.pipeline_builder import PipelineBuilder
from semantica.pipeline.pipeline_validator import PipelineValidator
builder = PipelineBuilder()
validator = PipelineValidator()
deps = validator.check_dependencies(builder)
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.
- 9d ago First seen · 229 lines · 0 tokens per session scan A c7bf4c39f965
validate is a skill published in the GitHub repository semantica-agi/semantica (12,329 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,140 tokens. 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
fairness-testing
Use when writing tests for any ML model, classifier, or AI system that produces outputs affecting people. Fairness tests must be written before the model is used in production.
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
launching-evals
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals…
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.