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/endogenai/dogma/agent-taxonomygit clone --depth 1 https://github.com/EndogenAI/dogmaWrote 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/endogenai/dogma/agent-taxonomy)<a href="https://agentmods.dev/agents/endogenai/dogma/agent-taxonomy"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/agent-taxonomy.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 | $0.00000 | $0.05919 |
| Opus 5 | $0.00000 | $0.02959 |
| Sonnet 5 | $0.00000 | $0.01184 |
| Haiku 4.5 | $0.00000 | $0.00592 |
Grade A, and why
agent-taxonomy 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.
How it starts
The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Taxonomy: Roles, Skills, and Fleet Constraints
Status: Final Research Question: What is the principled taxonomy of VS Code customization primitives — Roles (
.agent.md; VS Code: Custom Agents), Agent Skills (SKILL.md), and fleet constraints (AGENTS.md) — and what decision rules govern what belongs where? Date: 2026-03-07 Branch:feature/skills-research-and-adaptionRelated:AGENTS.md(guiding constraints),MANIFESTO.md(foundational axioms),ADR-006(skills adoption),docs/research/agent-skills-integration.md(prior Phase 1 synthesis)
Executive Summary
The VS Code customization stack has three first-class primitives with non-overlapping roles: Roles (.agent.md; VS Code: Custom Agents) encode who does a task — role-specific persona, posture, tool restrictions, and handoff graph; Agent Skills (SKILL.md) encode how a task is done — reusable workflow procedures and resources loadable on demand across any skills-compatible AI tool; and fleet constraints (AGENTS.md) encode what all agents must do — universal behaviours enforced across the entire fleet. The VS Code upstream term for .agent.md files is "Custom Agents" (since VS Code 1.106; previously "custom chat modes"); the EndogenAI project term is "Roles", reflecting the conceptual purpose of these files as defined roles in the fleet. The boundary between these three layers has a precise formulation: role bodies retain only what is role-exclusive, while anything a second agent or non-VS-Code tool could use becomes a skill, and anything every agent must do goes into AGENTS.md. The central risk is boundary erosion — role bodies that accumulate skill-level procedures (too thick) or that delegate so much they lose distinct persona identity (too thin) — and this synthesis provides decision rules to prevent both failure modes. The prior Phase 1 synthesis (agent-skills-integration.md) established the composition rule; this document formalises the full three-way taxonomy with pattern catalogs and actionable decision trees.
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.
- yesterday First seen · 409 lines · 0 tokens per session scan A 043fe4bb8270
agent-taxonomy 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 5,919 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.
Other agents, from other repositories
agent-system
An AgentSystem composes multiple Agents into a directed graph that Orloj executes as a coordinated workflow. The graph defines how messages flow between agents during task execution.
acx-implementer
AgentCortex /implement phase executor. Use when delegating implementation work that must follow agentic-os gates, evidence requirements, and skill injection.
acx-tester
AgentCortex /test phase executor. Use when delegating test verification that must follow the test skeleton, coverage delta, and evidence requirements per agentic-os governance.
board-workflow
This document describes the end-to-end workflow for AI-assisted issue resolution, from initial issue creation through merged PR.
claude-expression
DISCLAIMER: This document is managed exclusively by Claude Code. The repository admin (AndrewAltimit) does not manage this file and is not allowed to directly edit it. Any updates must come from Claude Code through collaborative sessions.
codebase-analysis-pipeline
This document describes a two-stage automated pipeline for continuous codebase improvement.