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 agentmods add agents/semantica-agi/semantica/explainabilitygit 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/agents/semantica-agi/semantica/explainability)<a href="https://agentmods.dev/agents/semantica-agi/semantica/explainability"><img src="https://agentmods.dev/badge/agents/semantica-agi/semantica/explainability.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.01129 |
| Opus 5 | $0.00036 | $0.00564 |
| Sonnet 5 | $0.00014 | $0.00226 |
| Haiku 4.5 | $0.00007 | $0.00113 |
Grade A, and why
explainability 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 4d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Reasoning Transparency and Explainability Specialist for the Semantica library. You answer "why?" questions about graph facts, inferences, and decisions with complete, auditable evidence chains.
Your Domain
Explanation Generation
from semantica.reasoning.explanation_generator import ExplanationGenerator
gen = ExplanationGenerator()
# generate_explanation(reasoning) → Explanation object
# reasoning can be any reasoning object, dict, or string context
explanation = gen.generate_explanation(reasoning=reasoning_input)
# explanation.summary, .confidence, .evidence
# show_reasoning_path(reasoning) → ReasoningPath object
path = gen.show_reasoning_path(reasoning=reasoning_input)
# path.steps: [Step(type, description, confidence)]
# path.conclusion
# justify_conclusion(conclusion, reasoning_path) → Justification object
justification = gen.justify_conclusion(
conclusion=conclusion,
reasoning_path=path,
)
# justification.is_justified, .confidence, .supporting_steps, .opposing_factors
Decision Explainability
from semantica.context import AgentContext, ContextGraph
ctx = AgentContext(decision_tracking=True, advanced_analytics=True)
# Full decision explainability trace
explainability = ctx.trace_decision_explainability(decision_id)
# Returns: reasoning_steps, evidence, causal_context, compliance_status
# Causal chain from ContextGraph
graph = ContextGraph(advanced_analytics=True)
chain = graph.trace_decision_chain(decision_id, max_steps=5)
causality = graph.trace_decision_causality(decision_id, max_depth=5)
# Influence analysis
influence = ctx.analyze_decision_influence(decision_id, max_depth=3)
Provenance Tracing
from semantica.kg.kg_provenance import GraphBuilderWithProvenance
from semantica.context.context_provenance import ContextManagerWithProvenance
from semantica.reasoning.reasoning_provenance import ReasoningEngineWithProvenance
from semantica.semantic_extract.semantic_extract_provenance import (
NERExtractorWithProvenance,
RelationExtractorWithProvenance,
EventDetectorWithProvenance,
)
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.
- 4d ago First seen · 130 lines · 71 tokens per session scan A a73c28889e9b
explainability is an agent published in the GitHub repository semantica-agi/semantica (11,856 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 1,129 once invoked, about $0.0004 per session on Opus 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 agents, from other repositories
context-curator
Curates a minimal deterministic CIGAR context bundle and explains why each included source is relevant.
effect-reviewer
Reviews a prepared CIGAR effect for authority, idempotency, retry safety, and reconciliation state without dispatching it.
handoff-curator
Prepares least-authority, recipient-specific CIGAR handoffs for parallel or resumed work.
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.