Claude Code
Anthropic's agentic command-line coding tool that runs agents and loads Agent Skills, including onchain skills.
Last release Sep 8, 2026 · Last commit Sep 4, 2026 · ★ 144,139
Overview
Claude Code is Anthropic's terminal-based agentic coding tool. It runs agents that can read, write, and execute, and supports Agent Skills (SKILL.md) and MCP servers, so onchain agent skills like Bankr, CryptoSkills, COTI, and the OpenSea and Base MCPs plug directly into it. It is a general-purpose harness, not an onchain agent itself; onchain capability comes from the skills and MCP servers you add.
Sato Score
76/100· HighHow open, active & verifiable — not a safety or returns grade.
- Maintenance & liveness
- 35/35
- Code transparency
- 12/20
- Interface verifiability
- 0/10
- Docs & demo
- 6/10
- Listing transparency & provenance
- 15/15
- Independent verification
- 8/10
Independently verified — listing reviewed against evidence, never self-reported.
Observed record — 57 daily checks since 2026-07-14
- Succeeded
- 57
- Failed
- 0
- Their error
- 0
- Unattributed
- 0
This is the share of our daily checks that succeeded — not an availability guarantee. A check can fail because the host was down, because our runner timed out, or because the network in between dropped it, and only the first of those is a fact about this project. Failures are split by what we can attribute; anything we cannot attribute is counted, not hidden. 49 of these checks predate 2026-09-01, when the probe counted a bot-block (HTTP 403) as a failure and recorded no reason for any failure. Rates spanning that date mix two definitions. Since then: 100%.
Last 30 days — to 2026-09-09, one point per UTC day
A gap is a day we have no attributable observation — never a zero. Thirty points is the whole shape the free layer carries; the daily rows behind it stay in the snapshot series.
Details
- Chains
- Unknown
- Agent types
- Agent Harness, Coding Agent, Skill Runtime
- Open source
- No
- Pricing
- Included with Claude paid plans / API usage
- Deploys as
- npmfrom project docs · 2026-06-25
- Works with
- Model Context Protocol, GitHub, VS Code, JetBrains, Slackfrom project docs · 2026-06-25
- Last checked
- 2026-09-08
Marketplace Signals
- ▸ Functional agent
Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.
Recent Activity
All news →Releases and posts from Claude Code, pulled from its GitHub and X.
claude-code v2.1.265
What's changed Added user.email and user.groups to the telemetry Claude Desktop and Cowork send through a Claude apps gateway, matching terminal sessions Added support for pointing --plugin-dir at a folder of plugins: each child folder with a manifest loads, and children added or removed while running are picked up Added a 1 GB cap on tool results saved to disk; the in-conversation preview says wh
claude-code v2.1.263
What's changed Bug fixes and reliability improvements
claude-code v2.1.261
What's changed Added an "Organization policy" line to /status and claude doctor that says why your organization's policy could not be loaded, such as a proxy not passing the endpoint through Added bashOutputMaxChars and taskOutputMaxChars settings to raise how much command and background-task output Claude receives inline before it is saved to a file, up to 128K characters Added --append-subagent-
claude-code v2.1.260
What's changed Added a diff panel that opens beside the conversation in fullscreen mode and shows your uncommitted changes as Claude edits; toggle it with /diff Added a likely cause for prompt-cache misses (e.g. tool definitions or system prompt changed, idle past the TTL) to /cost and the status line's prompt_cache field Added /reload-plugins to headless sessions, so it appears in the Claude Code
claude-code v2.1.259
What's changed Added managedMcpServers managed setting: organizations can provide HTTP/SSE MCP servers to every user (same entry shape as .mcp.json ); entries that name a command to run are skipped Added --permission-prompts none for unattended headless hosts: anything that would prompt is denied automatically while the active permission mode (including auto mode) keeps deciding Added recognition
Claude can now use your computer in the background in Claude Cowork and Claude Code. Give it something to do on your desktop and Claude clicks, types, and opens apps just like you would, while you wor
Claude can now use your computer in the background in Claude Cowork and Claude Code. Give it something to do on your desktop and Claude clicks, types, and opens apps just like you would, while you work on something else. https://t.co/AOiup03pQK
Listing History
Recorded changes to Claude Code's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.
- Sep 8, 2026New release published
- Sep 6, 2026New release published
- Jul 14, 2026Enriched: is agent
- Jun 25, 2026Enriched: deployment options, marketplace notes
- Jun 25, 2026Auto-enriched: creator name, creator profile url, supported integrations, has pricing
- Jun 16, 2026Edited: deploy spec
- Jun 12, 202651 releases trackedShowing the 2 most recent. Full release history is retained in the listing record.
- Jun 11, 2026Sato Hub began tracking this listing
Related Resources
Coinbase AgentKit
ActiveCoinbase's toolkit for giving AI agents wallets and the ability to take onchain actions.
Hyperliquid
ActiveOnchain perpetual futures and spot DEX running on its own L1 with an HyperEVM smart-contract layer.
ElizaOS
ActiveOpen-source TypeScript framework for building crypto-native multi-agent systems.
Is this your project?
Prove you control the domain and you can correct this page — description, links, tags, chains. Claiming proves control, not verification: it doesn't change the Sato Score or mark anything as audited.
Claim this listing →Cite this page
Sato Hub. "Claude Code — Sato Hub." Sato Hub, updated 2026-09-08, accessed 2026-09-09. https://satohub.ai/resources/claude-codeThis page is refreshed daily. Citations include the date so a reader can tell which snapshot a claim came from.
Join the Sato Hub Briefing
One email a week — the agents, tools, and infrastructure that actually shipped, and why they matter.