fleet-emergence-operationalization

fleet-emergence-operationalization is an agent for coding agents from EndogenAI/dogma. It costs 0 tokens per session (5,637 once invoked), scanned A, original, Apache-2.0.

A research model for how a group of coding agents can develop coordinated behaviour through shared files, workflows, and feedback rather than one central controller.

In plain words
What is it for?
Use it to study agent fleets, measure coordination over time, and define evidence for an emergence event.
Why use it?
It provides ways to tell genuine coordination from simple growth by tracking how agents' observations change the project’s lasting rules and tools.

Agent

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.

agentmods
npx agentmods add agents/endogenai/dogma/fleet-emergence-operationalization
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

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 fleet-emergence-operationalization

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/fleet-emergence-operationalization.svg)](https://agentmods.dev/agents/endogenai/dogma/fleet-emergence-operationalization)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/fleet-emergence-operationalization"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/fleet-emergence-operationalization.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 5,637 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 $0.00000 $0.05637
Opus 5 $0.00000 $0.02818
Sonnet 5 $0.00000 $0.01127
Haiku 4.5 $0.00000 $0.00564

Measured yesterday against content hash 3bd18d625904, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fleet-emergence-operationalization 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 yesterday.

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/fleet-emergence-operationalization.md · 426 lines

How it starts

The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Morphogenetic System Design Operationalization: Formal Model of Fleet Emergence

Research question: Can "emergent fleet topology" be formally defined using observable, measurable metrics grounded in session history evidence from the EndogenAI codebase? What minimum thresholds constitute a genuine emergence event, and how does this operationalization connect to morphogenetic engineering theory? Date: 2026-03-10 Closes: #168


1. Executive Summary

The Endogenic Development Methodology's H2 hypothesis — morphogenetic system design — claims that an agent fleet governed by distributed local encoding rules exhibits emergent coherent topology without central coordination. This document operationalizes that claim.

The endogenic fleet began with 14 agents on 2026-03-06 and reached 36 agents by 2026-03-10, a 157% increase over four days across five distinct milestone sprints. This growth trajectory is not the emergence phenomenon — growth alone is additive, not emergent. Emergence is observable in the back-propagation cycle: the feedback loop in which session observations by subagents cause durable changes to the substrate (AGENTS.md, agent files, CI configuration) that in turn alter the selection pressures governing all future sessions.

Four operational metrics are formally defined:

  1. Back-propagation cycles (BPC): substrate edits caused by session observations
  2. Agent role mutations (ARM): .agent.md scope changes per milestone
  3. Session citation density (SCD): MANIFESTO.md references per scratchpad per milestone
  4. Fleet topology delta (FTD): change in agent count + new inter-agent edge types per milestone

Three case studies from the docs/plans/ corpus provide measured evidence. The formal emergence model defines a minimum co-occurrence threshold: ≥3 of 4 metrics must exceed milestone-level thresholds simultaneously for an event to qualify as emergence rather than planned growth.

The operationalization grounds endogenic-design-paper.md §H2 in the morphogenetic engineering literature (Doursat et al., 2013; Green, 2023) while using exclusively endogenous session artifacts as evidence — implementing MANIFESTO.md §1. Endogenous-First at the research method level.

Read the full file on GitHub · 426 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. yesterday First seen · 426 lines · 0 tokens per session scan A 3bd18d625904

Subscribe to this mod's changes

fleet-emergence-operationalization is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 11d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,637 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.