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.
git clone --depth 1 https://github.com/bibinprathap/VeritasGraphWrote 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/bibinprathap/veritasgraph/decision-advisor)<a href="https://agentmods.dev/agents/bibinprathap/veritasgraph/decision-advisor"><img src="https://agentmods.dev/badge/agents/bibinprathap/veritasgraph/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.
<a href="https://agentmods.dev/agents/bibinprathap/veritasgraph/decision-advisor"><img src="https://agentmods.dev/badge/agents/bibinprathap/veritasgraph/decision-advisor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.01184 |
| Opus 5.5 | $0.00022 | $0.00474 |
| Sonnet 5.5 | $0.00011 | $0.00237 |
| Haiku 4.5 | $0.00006 | $0.00118 |
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 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.
This is a copy
92% identical to decision-advisor — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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 VeritasReason library. You focus on the full decision lifecycle: recording, querying, precedent search, causal analysis, policy compliance, and explainability.
Your Domain
Recording Decisions
from veritasreason.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 veritasreason.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 veritasreason.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")
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 · 127 lines · 56 tokens per session scan A 3f11ee6c7415
decision-advisor is an agent published in the GitHub repository bibinprathap/VeritasGraph (325 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 1,184 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to decision-advisor, differing in 14 lines, and is treated as a copy.
Other agents, from other repositories
rag-pipeline-reviewer
Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.
token
Optimizes LLM context windows through token budgeting, chunking strategy, and truncation design. Use when you need to control token spend, design a chunking pipeline, or audit token usage in a production AI system. Trigger with "design my token budget", "fix my context overflow".
bash
A command-line agent for running Bash shell commands, terminal tasks, and Git operations. Bash is a program for giving text commands to an operating system; Git tracks changes to code.
explore
An exploration agent for searching local files and the web, then combining findings into a factual report. It cannot create, edit, or delete local files.
git-summary
A Git commit-summary assistant that reads a code diff, meaning the changes between two versions, and writes one short description of the main change.
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.