A way to define and run teams of AI agents with Docker. Agents are configured in a YAML file with their instructions, models, tools, and optional sub-agents, and can use MCP for connecting to external tools.

Use it to configure multi-agent systems, connect agents to MCP tools, create agent teams with specialized roles, and run them locally with Docker cagent.

Managing several cooperating agents can otherwise require scattered configuration and manual setup. A single runtime configuration describes how the agents, tools, and handoffs fit together.

learn — Skill for Claude Code by Tyler-R-Kendrick/agent-skills

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.

Any agent

npx skills add Tyler-R-Kendrick/agent-skills --skill learn

Clone the repo

git clone --depth 1 https://github.com/Tyler-R-Kendrick/agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 57 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/learn/github.svg)](https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/learn)

Your own site

<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/learn"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/learn/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/learn"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 604 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00105	$0.00604
Opus 5.5	$0.00042	$0.00242
Sonnet 5.5	$0.00021	$0.00121
Haiku 4.5	$0.00011	$0.00060

Measured 2mo ago against content hash 4da239c71649, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

learn 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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/dist/learn.js, scripts/src/learn.ts, scripts/test/learn.test.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/ai/learn/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn

Use this skill to turn a user correction into a generalized steering rule. Keep STEERING.md as an index, and keep details in linked RDF/Turtle files under ~/.agents/.steering/.

This turns feedback loops into explicit, inspectable learnings. See correction-to-learning.md for the correction-to-learning model.

Route

IF the user corrects an agent response, read correction-to-learning.md and zpd-teaching-loop.md.
IF creating or updating steering artifacts, read steering-index-contract.md and rdf-contract.md.
IF using the deterministic helper, read cli-usage.md and run node skills/ai/learn/scripts/dist/learn.js.
ELSE answer normally and do not create steering entries.

Core Workflow

Identify the correction, the agent behavior it changes, and the broader class of future tasks it should affect.
Generalize the correction into a strategy or preference, not a one-off fact.
If memory is available, search for related prior corrections and add memory:// evidence links; keep facts in memory, not in steering.
Add evidence links to docs, instruction files, conversations, or other sources.
Use the CLI to write the RDF entry and regenerate STEERING.md.
Briefly teach the agent what reasoning move to practice next time.

Best Practices

Always store durable learnings as generalized strategies or preferences, not isolated task facts.
Keep STEERING.md as a conditional index and load linked RDF files only when the current task matches the entry.
Require evidence links for every learning so agents can inspect provenance before relying on the rule.
Use the zone of proximal development to explain the next reasoning move the correction teaches.
Prefer deterministic CLI writes over manual steering edits to avoid broken links, duplicate IDs, or stale index rows.

Read the full file on GitHub · 48 lines

Files

What ships with it

20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 48 lines · 105 tokens per session scan A 4da239c71649

Subscribe to this mod's changes

learn is a skill published in the GitHub repository Tyler-R-Kendrick/agent-skills (13 stars, last pushed 5mo ago), licensed MIT. It adds 105 tokens to every session and 604 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.

Building agents Learning and teaching

learn next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
learnTyler-R-Kendrick/agent-skills	Skill	13	5mo ago	MIT	A	105	Claude Code
hr-onboardingnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	62	Claude Code, Codex
book-mirrorgarrytan/gbrain	Skill	32k	yesterday	MIT	A	138	Claude Code
exam-forecastanthropics/claude-for-legal	Skill	9.9k	3d ago	Apache-2.0	A	73	Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep	Skill	19k	3d ago	MIT	A	81	Claude Code
eli5companion-inc/feynman	Skill	10k	6d ago	MIT	A	63	Claude Code, Codex
deck-course-modulenexu-io/html-anything	Skill	9.4k	25d ago	Apache-2.0	A	25	Claude Code, Codex