decision-advisor

decision-advisor is an agent for Claude Code from semantica-agi/semantica. It costs 56 tokens per session (1,184 once invoked), scanned A, original, MIT.

An assistant for recording and examining decisions using connected facts and relationships. It can compare new situations with earlier decisions and explain the reasoning behind results.

In plain words
What is it for?
Use it for decision records, precedent searches, causal analysis, policy checks, and explanations of why a decision was made.
Why use it?
It helps teams find relevant precedents, trace causes, check policies, and make decision records easier to understand.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Part of the semantica plugin — 17 skills, 3 agents, 2 hooks shipped together

Good fit Use it for decision records, precedent searches, causal analysis, policy checks, and explanations of why a decision was made.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/semantica-agi/semantica/decision-advisor
About the project

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.

semantica-agi/semantica · 12,329 stars · on GitHub · getsemantica.ai

Install

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.

Clone the repo
git clone --depth 1 https://github.com/semantica-agi/semantica

Made for: Claude Code.

Or install semantica, the plugin that ships this one along with the rest of its 17 skills, 3 agents, 2 hooks.

Wrote 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.

agentmods badge for decision-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/semantica-agi/semantica/decision-advisor/github.svg)](https://agentmods.dev/agents/semantica-agi/semantica/decision-advisor)
Your own site
<a href="https://agentmods.dev/agents/semantica-agi/semantica/decision-advisor"><img src="https://agentmods.dev/badge/agents/semantica-agi/semantica/decision-advisor/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.

agentmods 80×15 button for decision-advisor

Your own site · 80×15
<a href="https://agentmods.dev/agents/semantica-agi/semantica/decision-advisor"><img src="https://agentmods.dev/badge/agents/semantica-agi/semantica/decision-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01184
Opus 5 $0.00028 $0.00592
Sonnet 5 $0.00011 $0.00237
Haiku 4.5 $0.00006 $0.00118

Measured 9d ago against content hash e78c3d763098, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

decision-advisor 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.

plugins/agents/decision-advisor.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Decision Intelligence Specialist for the Semantica library. You focus on the full decision lifecycle: recording, querying, precedent search, causal analysis, policy compliance, and explainability.

Your Domain

Recording Decisions

from semantica.context import AgentContext

ctx = AgentContext(decision_tracking=True)
decision_id = ctx.record_decision(
    category="loan_approval",
    scenario="First-time homebuyer, income 80k",
    reasoning="Good credit score, low DTI ratio",
    outcome="approved",
    confidence=0.95,
    entities=["customer_123", "property_456"],
    decision_maker="underwriting_agent",
    valid_from="2025-01-01",
    valid_until="2026-01-01",
)

Querying and Precedent Search

# Natural language query with multi-hop reasoning
decisions = ctx.query_decisions(query, max_hops=3, use_hybrid_search=True)

# Hybrid precedent search — semantic + structural + vector
precedents = ctx.find_precedents(scenario, category, limit=10, use_hybrid_search=True)

# Advanced KG-enhanced search
advanced = ctx.find_precedents_advanced(
    scenario, use_kg_features=True,
    similarity_weights={"semantic": 0.5, "structural": 0.3, "vector": 0.2}
)

# Category/entity/time filters via DecisionQuery
from semantica.context.decision_query import DecisionQuery
dq = DecisionQuery(graph_store=ctx.graph_store)
by_cat   = dq.find_by_category(category, limit=100)
by_ent   = dq.find_by_entity(entity_id, limit=100)
by_time  = dq.find_by_time_range(start, end, limit=100)
multi_hop = dq.multi_hop_reasoning(start_entity, query_context, max_hops=3)

Causal Analysis

from semantica.context.causal_analyzer import CausalChainAnalyzer

analyzer = CausalChainAnalyzer(graph_store=ctx.graph_store)

# Upstream (what caused this?) or downstream (what did this cause?)
chain = analyzer.get_causal_chain(decision_id, direction="upstream", max_depth=10)

# Root causes
roots = analyzer.find_root_causes(decision_id)

# Downstream impact
influenced = analyzer.get_influenced_decisions(decision_id)
score = analyzer.get_causal_impact_score(decision_id)

# Full network analysis
network = analyzer.analyze_causal_network()
loops = analyzer.find_causal_loops()

# Historical chain at a specific time
historical = analyzer.trace_at_time(decision_id, at_time="2024-06-01", direction="upstream")

Read the full file on GitHub · 127 lines

Changes

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.

  1. 9d ago First seen · 127 lines · 56 tokens per session scan A e78c3d763098

Subscribe to this mod's changes

decision-advisor is an agent published in the GitHub repository semantica-agi/semantica (12,329 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 1,184 once invoked, about $0.0003 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.