The batteries-included agent harness.
Deep Agents is an extensible agent harness that provides an out-of-the-box agent for long, multi-step tasks, with features such as planning, sub-agents, filesystem access, context management, memory, and human approval of tool calls. It is used by developers building agents with different language models, and its catalogue entries extend the harness with reusable skills, MCP servers, and instructions.
This repository also configures its own agents. See what deepagents tells them →
Skill Claude CodeCodex ✓ vendor
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
Skill Claude CodeCodex ✓ vendor
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
Skill Claude CodeCodex ✓ vendor
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
Skill Claude CodeCodex ✓ vendor
Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append new preferences when the user gives durable feedback.
Skill Claude CodeCodex ✓ vendor
Break down a coding task into a structured implementation plan with clear steps, file identification, and risk assessment.
Skill Claude CodeCodex ✓ vendor
Analyze competitors in a given market segment. Trigger on: competitive landscape, competitor analysis, market comparison, competitive positioning.
Skill Claude CodeCodex ✓ vendor
Perform a market analysis for a product category or segment. Trigger on: market analysis, market size, TAM SAM SOM, market opportunity, industry analysis.
Skill Claude CodeCodex ✓ vendor
Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical summaries, anomaly detection, or large-scale data profiling.
Skill Claude CodeCodex ✓ vendor
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
Skill Claude CodeCodex ✓ vendor
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
Skill Claude CodeCodex ✓ vendor
Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing. Triggers when the user provides large documents or needs bulk document analysis.
Skill Claude CodeCodex ✓ vendor
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.
Skill Claude CodeCodex ✓ vendor
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
Skill Claude CodeCodex ✓ vendor
Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use to look up the current thread's title or name, as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata…
Skill Claude CodeCodex ✓ vendor
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
Skill Claude CodeCodex ✓ vendor
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an…
Skill Claude CodeCodex ✓ vendor
Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv, look up preprints, find academic articles in physics, math, CS, biology, statistics, or related fields.
Skill Claude CodeCodex ✓ vendor
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.
Skill Claude CodeCodex ✓ vendor
Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.
Skill Claude CodeCodex ✓ vendor
Review Talon tool placement and defensive prompts when requested or when adding or changing tools or subagents; apply confirmed changes and verify active capabilities.
Skill Claude CodeCodex ✓ vendor
Check secret handling, staged changes and push targets, destructive Git operations, Docker image hygiene, and new dependencies before consequential coding actions. Use for commits, pushes, container builds or publishes, dependency additions, and explicit safety reviews.
Skill Claude CodeCodex ✓ vendor
Discover plugins from configured dcode marketplaces when a capability is missing or the user asks about available, disabled, or not-yet-installed plugins and connected marketplaces.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: