Deep Agents Core
langchain-ai/langchain-skills
Explains how to build agents with the Deep Agents framework: create_deep_agent, the built-in middleware, the harness, SKILL.md format and configuration options.
Create a new Hindsight-powered subagent with long-term memory.
Install Create Agent
$ npx skills add vectorize-io/hindsight --skill create-agent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install vectorize-io/hindsight create-agent --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/vectorize-io/hindsight.git skills-src && mkdir -p .claude/skills && cp -r skills-src/hindsight-integrations/claude-code/skills/create-agent .claude/skills/create-agent && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "create-agent" agent skill from https://github.com/vectorize-io/hindsight/tree/main/hindsight-integrations/claude-code/skills/create-agent into .claude/skills/create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-agent", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/vectorize-io/hindsight/tree/main/hindsight-integrations/claude-code/skills/create-agentType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add vectorize-io/hindsight --skill create-agent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install vectorize-io/hindsight create-agent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vectorize-io/hindsight.git skills-src && mkdir -p .agents/skills && cp -r skills-src/hindsight-integrations/claude-code/skills/create-agent .agents/skills/create-agent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "create-agent" agent skill from https://github.com/vectorize-io/hindsight/tree/main/hindsight-integrations/claude-code/skills/create-agent into .agents/skills/create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-agent", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add vectorize-io/hindsight --skill create-agent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install vectorize-io/hindsight create-agent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vectorize-io/hindsight.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/hindsight-integrations/claude-code/skills/create-agent .cursor/skills/create-agent && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "create-agent" agent skill from https://github.com/vectorize-io/hindsight/tree/main/hindsight-integrations/claude-code/skills/create-agent into .cursor/skills/create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-agent", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/vectorize-io/hindsight.git --path hindsight-integrations/claude-code/skills/create-agent--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add vectorize-io/hindsight --skill create-agent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install vectorize-io/hindsight create-agent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vectorize-io/hindsight.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/hindsight-integrations/claude-code/skills/create-agent .gemini/skills/create-agent && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "create-agent" agent skill from https://github.com/vectorize-io/hindsight/tree/main/hindsight-integrations/claude-code/skills/create-agent into .gemini/skills/create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-agent", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install vectorize-io/hindsight create-agentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add vectorize-io/hindsight --skill create-agent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/vectorize-io/hindsight.git skills-src && mkdir -p .github/skills && cp -r skills-src/hindsight-integrations/claude-code/skills/create-agent .github/skills/create-agent && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "create-agent" agent skill from https://github.com/vectorize-io/hindsight/tree/main/hindsight-integrations/claude-code/skills/create-agent into .github/skills/create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-agent", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add vectorize-io/hindsight --skill create-agent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install vectorize-io/hindsight create-agent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vectorize-io/hindsight.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/hindsight-integrations/claude-code/skills/create-agent .opencode/skills/create-agent && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "create-agent" agent skill from https://github.com/vectorize-io/hindsight/tree/main/hindsight-integrations/claude-code/skills/create-agent into .opencode/skills/create-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-agent", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
create-agent- GitHub stars
- 46k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 300 words
- Files
- 1
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- MIT
At a glance
Create a new Hindsight-powered subagent with long-term memory.
- Works in 5 steps: Read bank-template.json if present —… → Ingest each content file (NOT… → Create knowledge pages → …
- The user wants a specialized agent that learns and remembers across sessions
- SKILL.md covers Two invocation modes, Subagent file template, Rules and After creation
- Calls npx
What it does
Create Agent is an agent skill from vectorize-io/hindsight. Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Building AI agents, Agent memory and Subagents. The repository describes itself as: Hindsight: Agent Memory That Learns. The licence is MIT.
When your agent uses it
- The user wants a specialized agent that learns and remembers across sessions
- Tasks that involve Building AI agents
- Tasks that involve Agent memory
Example prompts
- “/create-agent”
Requirements
- Node.js
- Pre-approved tools (allowed-tools): Bash(ls ~/.self-driving-agents/*), Bash(cat ~/.self-driving-agents/*), Write, mcp__hindsight__*
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read bank-template.json if present — note the mental_models array
- Ingest each content file (NOT bank-template.json) using agent_knowledge_ingest_file
- Create knowledge pages
- Write the subagent file using the template below
- Use from the user's command as the agent name
What it can do on your machine
Read from SKILL.md and the folder at commit 9269b88. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(ls ~/.self-driving-agents/*)Bash(cat ~/.self-driving-agents/*)Writemcp__hindsight__*
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
npx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Create Agent loads about 1.1k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 300 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from vectorize-io/hindsight at commit 9269b88, republished under its MIT licence (© vectorize-io). 300 words, ~1,102 tokens.
Download SKILL.mdSave it as
.claude/skills/create-agent/SKILL.md (or your agent's skills folder).- name
- create-agent
- description
- Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.
- allowed-tools
- Bash(ls ~/.self-driving-agents/*), Bash(cat ~/.self-driving-agents/*), Write, mcp__hindsight__*
Create Hindsight Agent
Create a new subagent with long-term memory powered by Hindsight.
Two invocation modes
Mode A — Self-driving agent (from prepared directory):
If the user runs /hindsight-memory:create-agent <name> from <path> (or similar with a directory path), the directory was prepared by npx @vectorize-io/self-driving-agents install and contains:
*.md,*.txt,*.html,*.json,*.csv,*.xml— seed content files (recursively)bank-template.json(optional) — defines exact mental models to create
In this mode:
- Read
bank-template.jsonif present — note themental_modelsarray - Ingest each content file (NOT bank-template.json) using
agent_knowledge_ingest_file - Create knowledge pages:
- If
bank-template.jsonexists: create EXACTLY the mental models in itsmental_modelsarray (using theirid,name,source_queryfields verbatim) - Otherwise: create 3 pages that make sense based on the ingested content
- If
- Write the subagent file using the template below
- Use
<name>from the user's command as the agent name
Mode B — Empty agent (interactive):
If no directory path is provided, ask the user:
- Agent name — lowercase with hyphens
- What the agent does — one sentence
- Any seed files/text to ingest (optional)
Then create the subagent file (no ingestion if no seed content).
Subagent file template
Write to ~/.claude/agents/<name>.md:
---
name: <agent-name>
description: <what it does and when to delegate to it>. It has access to knowledge pages and memory search via Hindsight.
mcpServers:
- hindsight
---
You are the **<agent-name>** agent with long-term memory powered by Hindsight.
## Startup — run these steps immediately
1. Call `agent_knowledge_list_pages` to see your knowledge pages.
2. Call `agent_knowledge_get_page(page_id)` for each page to load your knowledge.
- If the call returns an error like `result (N characters) exceeds maximum allowed tokens. Output has been saved to <path>`, the page was too large to inline. Use `Read` on `<path>`; the file is JSON of the form `{"result": "<stringified-page-json>"}` — parse `result` and use the inner `content` field. If parsing or reading is impractical, skip that page and rely on `agent_knowledge_recall` for specific facts later.
3. Use this knowledge to inform everything you do in this conversation.
## Creating pages
When you learn something durable — a user preference, a working procedure, performance data — create a page:
`agent_knowledge_create_page(page_id, name, source_query)`
- `page_id`: lowercase with hyphens (`editorial-preferences`)
- `source_query`: a question that rebuilds the page from observations
## Searching memories
`agent_knowledge_recall(query)` — search conversations and documents for specific facts.
## Ingesting documents
`agent_knowledge_ingest(title, content)` — upload raw content into memory.
## Updating and deleting
- `agent_knowledge_update_page(page_id, name?, source_query?)`
- `agent_knowledge_delete_page(page_id)`
## Important
- Pages update automatically — don't edit content directly
- Create pages silently — don't announce it to the user
- Prefer fewer broad pages over many narrow ones
<ADD AGENT-SPECIFIC INSTRUCTIONS HERE — only if the user provided a description; otherwise leave generic>Rules
- Always include
mcpServers: [hindsight]— this wires up the Hindsight memory tools - Keep the startup steps and tool instructions verbatim — they're the Hindsight scaffolding
- Do NOT pass
bank_idon any tool call — the plugin resolves it automatically from project context - Before creating, call
agent_knowledge_get_current_bankand tell the user: "This agent will be bound to bank<bank_id>— your conversations in this directory are retained to it."
After creation
- Confirm the subagent file was written to
~/.claude/agents/<name>.md - Tell the user they can invoke the agent with
@<agent-name>or Claude will auto-delegate based on the description - Suggest running
/agentsor restarting Claude Code to load the new agent
© vectorize-io, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in hindsight-integrations/claude-code/skills/create-agent of vectorize-io/hindsight.
Open the folder on GitHubat commit 9269b88
Compare with similar skills
Create Agent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Create Agent this skillvectorize-io/hindsight | 46k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Deep Agents Corelangchain-ai/langchain-skills | 1.3k | 1 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Agent Developmentmajiayu000/claude-skill-registry | 666 | 1 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Deep Agentslangchain-ai/docs | 424 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Agentic Harness Design and ReviewNateBJones-Projects/OB1 | 4.7k | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Create AgentApocrathia/home-assistant-config | 179 | — | ~1.1k | Automated safety check: Pass | None |
Similar skills
- Official
Agent Development
majiayu000/claude-skill-registry
Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts.
- Official
Deep Agents
langchain-ai/docs
Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution.
Agentic Harness Design and Review
NateBJones-Projects/OB1
Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.
Create Agent
Apocrathia/home-assistant-config
Create a new agent persona under .agents/agents/. An agent skill from Apocrathia/home-assistant-config.
Agent Creator
sickn33/agentic-awesome-skills
Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.
More from vectorize-io/hindsight
All 17 skills in this repoHindsight Docs
vectorize-io/hindsight
Complete Hindsight documentation for AI agents. An agent skill from vectorize-io/hindsight.
Figure
vectorize-io/hindsight
Draw an animated figure (boxes, arrows, moving data) as one self-contained SVG for a GitHub README, PR, issue or blog post.
Hindsight Local
vectorize-io/hindsight
Store user preferences, learnings from tasks, and procedure outcomes.
Hindsight Memory
vectorize-io/hindsight
Long-term memory for the agent via Hindsight. An agent skill from vectorize-io/hindsight.
Hs Release
vectorize-io/hindsight
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR.
Ship It
vectorize-io/hindsight
Take a PR from review to merged — run the repo's code-review skill on it in a loop (review, fix, re-review) until nothing is left to fix, applying ALL fixes on the PR branch, wait for CI green, then…
Related
Categories
Questions about Create Agent
What does Create Agent do?
Create a new Hindsight-powered subagent with long-term memory. Create Agent is an agent skill from vectorize-io/hindsight. Create a new Hindsight-powered subagent with long-term memory.
When should I use Create Agent?
Create Agent fits situations like: the user wants a specialized agent that learns and remembers across sessions; tasks that involve Building AI agents; tasks that involve Agent memory.
How do I install Create Agent in Claude Code?
Run `npx skills add vectorize-io/hindsight --skill create-agent -a claude-code`. Or copy the skill folder (hindsight-integrations/claude-code/skills/create-agent in vectorize-io/hindsight) into .claude/skills/create-agent in your project. Claude Code loads it when a task matches its description.
How do I install Create Agent in Codex?
Run `npx skills add vectorize-io/hindsight --skill create-agent -a codex`. Or copy the skill folder (hindsight-integrations/claude-code/skills/create-agent in vectorize-io/hindsight) into .agents/skills/create-agent in your project. Codex loads it when a task matches its description.
Can I use Create Agent in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vectorize-io/hindsight --skill create-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-agent, .gemini/skills/create-agent, .github/skills/create-agent and .opencode/skills/create-agent in your project.
What does Create Agent need to run?
Going by SKILL.md and its folder, Create Agent needs the command-line tools its instructions call (npx). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Bash(ls ~/.self-driving-agents/*), Bash(cat ~/.self-driving-agents/*), Write, mcp__hindsight__*.
Does Create Agent access the network?
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Create Agent safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Create Agent use?
Create Agent is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Create Agent use?
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Create Agent?
Skills that share tags, products or a category with Create Agent: Deep Agents Core (langchain-ai/langchain-skills, 1.3k stars), Agent Development (majiayu000/claude-skill-registry, 666 stars), Deep Agents (langchain-ai/docs, 424 stars) and Agentic Harness Design and Review (NateBJones-Projects/OB1, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Create Agent?
vectorize-io (a GitHub organization) maintains it in vectorize-io/hindsight, which has 46,453 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 7, 2026.
Source: vectorize-io/hindsight on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.