agent-skills-integration

agent-skills-integration is an agent for Claude Code from EndogenAI/dogma. It costs 0 tokens per session (5,352 once invoked), scanned A, original, Apache-2.0.

A research summary about Agent Skills, an open format for packaging reusable instructions in SKILL.md files for AI coding agents. It explains how these skills differ from agent role files and how VS Code discovers them.

In plain words
What is it for?
Use it when designing an agent setup with reusable skills, role definitions, automatic discovery, or layered instructions.
Why use it?
It helps teams decide where workflow instructions belong and how agents can load detailed guidance only when a task requires it.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

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/agent-skills-integration
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

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 agent-skills-integration

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/agent-skills-integration.svg)](https://agentmods.dev/agents/endogenai/dogma/agent-skills-integration)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/agent-skills-integration"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/agent-skills-integration.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 5,352 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 $0.05352
Opus 5 $0.00000 $0.02676
Sonnet 5 $0.00000 $0.01070
Haiku 4.5 $0.00000 $0.00535

Measured 2d ago against content hash 7ae7165d4012, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-skills-integration 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/agent-skills-integration.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Skills Integration — Research Synthesis

Status: Final Research Question: How do VS Code Agent Skills (agentskills.io open standard) complement the existing .agent.md fleet, what is the canonical composition rule, and what is the optimal integration path for the EndogenAI Workflows repository? Date: 2026-03-07 Related: AGENTS.md (guiding constraints), MANIFESTO.md (Algorithms Before Tokens axiom), docs/guides/agents.md, docs/plans/2026-03-07-issue-60-agent-skills.md


1. Executive Summary

Agent Skills are an open standard (agentskills.io, developed by Anthropic) for packaging workflow expertise as portable SKILL.md files that AI agents load on demand. In VS Code, skills are stored in .github/skills/ and discovered automatically by GitHub Copilot — only metadata (~100 tokens per skill) is loaded at startup, with full instructions loaded only when relevant. Skills sit at the tactical layer of the VS Code customization stack: they encode how to do a task (procedures, conventions, templates), while .agent.md Roles encode who does it (persona, posture, tool restrictions, handoff logic). This separation is the canonical composition rule.

For this repository, skills are the precise implementation of the Algorithms Before Tokens axiom from MANIFESTO.md: workflow knowledge that currently lives in docs/guides/, CONTRIBUTING.md, and agent bodies can be extracted into skills, encoded once, and inherited across all sessions, tools, and platforms without repeated prompting overhead. The three highest-priority candidates — session-management, deep-research-sprint, and conventional-commit — are available for immediate implementation.


2. Hypothesis Validation

This section validates the seven research questions (Q1–Q7) from Issue #60.

Q1 — Skills vs Agents: The Composition Rule

Read the full file on GitHub · 329 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 · 329 lines · 0 tokens per session scan A 7ae7165d4012

Subscribe to this mod's changes

agent-skills-integration 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 5,352 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.