dynamic-agent-navigation

dynamic-agent-navigation is an agent for Claude Code from EndogenAI/dogma. It costs 0 tokens per session (2,729 once invoked), scanned A, original, Apache-2.0.

A study of graph-based routing for AI agents, where workflow states and possible actions are represented as connected paths and algorithms choose a route.

In plain words
What is it for?
Use it to design agent navigation, compare graph and state-machine approaches, and route tasks through multi-step workflows.
Why use it?
It can replace hard-to-maintain nested if/then decisions with an explicit map of states, transitions, and route weights.

Agent for Claude Code

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

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is **Related**: [`data/phase-gate-fsm.yml`](../../../data/phase-gate-fsm.yml) (endogenous FSM);.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 dynamic-agent-navigation

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/dynamic-agent-navigation.svg)](https://agentmods.dev/agents/endogenai/dogma/dynamic-agent-navigation)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/dynamic-agent-navigation"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/dynamic-agent-navigation.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,729 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02729
Opus 5 $0.00000 $0.01365
Sonnet 5 $0.00000 $0.00546
Haiku 4.5 $0.00000 $0.00273

Measured 2d ago against content hash f7a98d3beffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dynamic-agent-navigation 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 2d 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.

docs/research/agents/dynamic-agent-navigation.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dynamic AI Agent Navigation: Graph Routing Algorithms for Decision Workflows

Research question: Is it feasible to replace static "if/then" decision trees in agent workflows with navigable weighted knowledge graphs, enabling classical routing algorithms (A*, Dijkstra) to determine the most efficient, cost-effective, or reliable path to a goal state?

Date: 2026-03-14 Research Issue: #203 Related: data/phase-gate-fsm.yml (endogenous FSM); data/delegation-gate.yml (endogenous routing table); docs/research/endogenic-design-paper.md (H1, H4 framework)


Executive Summary

Graph routing algorithms — A*, Dijkstra, shortest-path traversal — are a natural fit for agent navigation when workflow state can be encoded as a weighted directed graph. This synthesis evaluates three architectural options (LangGraph, NetworkX, and native FSM/YAML) against the three core research questions from issue #203: state-as-coordinates, dynamic weighting, and Markdown-to-Graph schema design.

Key finding: This codebase already instantiates the core primitives. data/phase-gate-fsm.yml is a working navigable state graph; data/delegation-gate.yml is a working routing table. The highest-value next step is not adopting LangGraph, but extending these endogenous artifacts with edge weights and a NetworkX-backed path-analysis script.

The Algorithms Before Tokens axiom (MANIFESTO.md §2) is directly instantiated by this approach: encoding workflow routing as a data structure (YAML graph) that a deterministic algorithm can traverse is strictly superior to re-deriving routing logic via token burn each session.


Hypothesis Validation

H1 — State-as-Coordinates is tractable with existing FSM artifacts

Hypothesis: An agent's current "position" in a workflow can be represented as a coordinate in a multi-dimensional state space, enabling graph-based navigation.

Read the full file on GitHub · 256 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. 2d ago First seen · 256 lines · 0 tokens per session scan A f7a98d3beffd

Subscribe to this mod's changes

dynamic-agent-navigation is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,729 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 2026-09-03.