commandcode.ai valid
Command Code
Command Code is a frontier coding agent that builds software and continuously learns your coding taste. It ships full-stack projects, features, fixes bugs, writes tests, and refactors — all while learning how you write code. Powered by the meta neuro-symbolic AI model `taste-1` with continuous reinforcement learning.
For agents: Frontier coding agent CLI that builds and refactors software, learns coding style via the taste-1 model; docs cover install, workflows and CLI reference.
coding agenttaste-1 modelclireinforcement learningsoftware development
Their llms.txt
The beginning of the file, from our validated copy saved 2026-10-24T22:17:30.761Z. Cached copy · Source on commandcode.ai
# Command Code
> Command Code is a frontier coding agent that builds software and continuously learns your coding taste. It ships full-stack projects, features, fixes bugs, writes tests, and refactors — all while learning how you write code. Powered by the meta neuro-symbolic AI model `taste-1` with continuous reinforcement learning.
Install and run:
```
npm i -g command-code
cd your-project && cmd
```
Important notes:
- Command Code is a CLI-first terminal agent — run `cmd` in any project directory to start an interactive session
- **Taste** is the core differentiator: a personalized model that learns your coding style, patterns, and preferences automatically from every accept, reject, and edit
- Taste profiles are stored locally in `.commandcode/taste/` and can be shared via `npx taste push/pull`
- Custom instructions are set via `AGENTS.md` files (project-level or user-level at `~/.commandcode/AGENTS.md`)
- Agent Skills (`.commandcode/skills/`) extend Command Code with specialized knowledge and workflows following the [Agent Skills open standard](https://agentskills.io)
- MCP (Model Context Protocol) servers connect Command Code to external tools and services (databases, APIs, GitHub, Notion, etc.)
- Permission modes: **Standard** (confirmation required), **Plan** (read-only exploration), **Auto-Accept** (no confirmation). Toggle with `Shift+Tab`
- Checkpoints are created automatically before file modifications; rewind with `Esc Esc` or `/rewind`
## Docs
- [Quickstart](https://commandcode.ai/docs/quickstart): Install Command Code, authenticate, enable taste learning, and run your first prompt in minutes
- [Taste](https://commandcode.ai/docs/taste): How the `taste-1` meta neuro-symbolic AI model learns your coding style through continuous reinforcement learning
- [Workflows](https://commandcode.ai/docs/workflows): Step-by-step recipes for everyday tasks — understand codebases, fix bugs, refactor, write tests, create PRs, review PRs, and more
- [Interactive Mode](https://commandcode.ai/docs/core-concepts/interactive-mode): Complete reference for slash commands, keyboard shortcuts (`Shift+Tab`, `Ctrl+T`, `Ctrl+O`, `Alt+P`, `Ctrl+G`), and input modes
- [CLI Reference](https://commandcode.ai/docs/reference/cli): All CLI flags (`--resume`, `--continue`, `--print`, `--yolo`, `--plan`, `--add-dir`), subcommands (`info`, `status`, `update`, `taste`, `mcp`), and taste commands (`npx taste push/pull/list/lint`)
- [Memory (AGENTS.md)](https://commandcode.ai/docs/core-concepts/memory): Set custom instructions via project-level (`./AGENTS.md`) or user-level (`~/.commandcode/AGENTS.md`) memory files
- [Custom Agents](https://commandcode.ai/docs/core-concepts/custom-agents): Create subagents via `/agents` — project (`.commandcode/agents/`) or personal (`~/.commandcode/agents/`), generate with Command Code or manual Markdown config
- [Plan Mode & Auto-Accept](https://commandcode.ai/docs/core-concepts/plan-mode): Separate reasoning from execution — Plan
…
Related sites
Similar publisher descriptions and documentation. Similarity does not imply affiliation or equivalent capabilities.
| Domain | Title | Category | Country | Authority | llms.txt | llms-full.txt | Save |
|---|---|---|---|---|---|---|---|
| claude.com | Claude Code Docs | documentation Developer tools AI and machine learning +1 | US | 73 | ✓ | ✓ | |
| ampcode.com | Amp | documentation AI agents and MCP Developer tools | US | 59 | ✓ | ||
| openagents.com | OpenAgents | interface AI agents and MCP AI and machine learning | — | 50 | ✓ | ✓ | |
| claudekit.cc | ClaudeKit Documentation | documentation Marketing Developer tools +2 | SG | 48 | ✓ | ✓ | |
| warp.dev | Warp | documentation Developer tools AI agents and MCP | US | 66 | ✓ | ✓ | |
| emdash.com | Emdash | documentation AI agents and MCP Developer tools | US | 52 | ✓ | ||
| chatgpt.com | Codex | documentation AI and machine learning Developer tools +1 | — | 72 | ✓ | ✓ | |
| overhand.dev | Overhand | documentation Developer tools AI agents and MCP | — | 45 | ✓ | ✓ |
Machine-readable: GET /v1/resolve?q=commandcode.ai · GET /v1/domain/commandcode.ai · this page as Accept: application/json or text/markdown · MCP lookup_domain
Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.
Own or manage this website?
If you own or manage commandcode.ai, you can update its listing and review file health, discovery activity and score history.
Manage this listing — optional
What verification unlocks
See how your site is discovered—and control what agents see.
- See your website in the map
Review your indexed topics, nearby publishers sharing headings, measured listing exposure and map snapshots in a private report for your website.
- Control what agents see
Edit your listing description, tags, public contact details and additional llms.txt paths. Publish your terms for automated access, attribution and pricing.
- Make your profile eligible for search
A valid, listed, unblocked, verified profile can appear in our publisher sitemap and become eligible for search-engine visibility. Search engines decide what to index and rank.
- Appear in our llms-full.txt
Eligible verified publishers are listed by name, with their file links and summaries, in the service overview agents can read.
Free. No account registration, backlink or payment required. Public discovery remains available without verification.
Let your coding agent verify it
If your coding agent is authorized to manage this website, paste these instructions into it.
Claim my listing on Agent Web Map for commandcode.ai:
1. POST https://agentwebmap.com/v1/sites/commandcode.ai/claims and keep claim_id and claim_secret private.
2. Publish the verification line "AgentWebMap verification: <token>" (token from step 1) in https://commandcode.ai/llms.txt, or use the DNS, meta-tag or well-known method the response describes. This only verifies the listing; your website and domain remain yours.
3. POST https://agentwebmap.com/v1/sites/commandcode.ai/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/commandcode.ai).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verifyCorrections or removal requests: contact the directory.