surshar / claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Built by Anthropic · github.com/anthropics
Large file, diff not shown.
| @@ -6,8 +6,37 @@ | ||
| 6 | 6 | <author><name>Anthropic</name></author> |
| 7 | 7 | <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md"/> |
| 8 | 8 | <link rel="self" type="application/atom+xml" href="https://raw.githubusercontent.com/anthropics/claude-code/main/feed.xml"/> |
| 9 | - <updated>2026-07-08T00:27:43Z</updated> | |
| 9 | + <updated>2026-07-08T21:21:58Z</updated> | |
| 10 | 10 | <entry> |
| 11 | + <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.205</id> | |
| 12 | + <title>Claude Code v2.1.205</title> | |
| 13 | + <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.205"/> | |
| 14 | + <updated>2026-07-08T21:21:58Z</updated> | |
| 15 | + <content type="html"><p>• Added an auto mode rule that blocks tampering with session transcript files</p> | |
| 16 | +<p>• Fixed --json-schema silently producing unstructured output when the schema was invalid, and schemas using the format keyword being rejected</p> | |
| 17 | +<p>• Fixed a message sent while Claude was working being silently lost when the turn ended at the --max-turns limit</p> | |
| 18 | +<p>• Fixed Windows worktree removal deleting files outside the worktree when an NTFS junction or directory symlink existed inside it</p> | |
| 19 | +<p>• Fixed background agents staying shown as "failed" or "completed" in the agent list after being resumed with SendMessage</p> | |
| 20 | +<p>• Fixed background jobs flipping from "needs input" back to "working" in the agent list when the agent's turn contained no readable text</p> | |
| 21 | +<p>• Fixed claude attach erroring when a background agent was mid-upgrade restart instead of waiting for it to come back</p> | |
| 22 | +<p>• Fixed session-to-PR linking missing a PR created in a Bash call whose output exceeded the 30K inline limit</p> | |
| 23 | +<p>• Fixed claude mcp add-from-claude-desktop getting stuck when a server name contains unsupported characters; invalid names are now reported and remaining servers still import</p> | |
| 24 | +<p>• Fixed a plugin LSP server that fails to initialize preventing a valid LSP server from another plugin handling the same file extension</p> | |
| 25 | +<p>• Fixed a Windows crash when the directory Claude was launched from is deleted, locked, or unmounted while a command is running</p> | |
| 26 | +<p>• Fixed a crash when a file watcher was closed while a directory scan was still in flight</p> | |
| 27 | +<p>• Fixed project verify skills being rewritten on every session instead of only when a documented command changed</p> | |
| 28 | +<p>• Fixed the agent view rendering one line too high and clipping its header when the job list slightly overflowed the screen</p> | |
| 29 | +<p>• Fixed background tasks in the web and mobile Remote Control panels showing stale "Running" status by forwarding full task state on every membership change</p> | |
| 30 | +<p>• Improved auto mode to ask before running rm -rf on a variable it can't resolve from context</p> | |
| 31 | +<p>• Auto-update binary downloads now stream to disk instead of buffering in memory, cutting the updater's peak memory usage by roughly 400 MB</p> | |
| 32 | +<p>• Background task notifications now explicitly state that no human input has occurred, preventing fabricated in-transcript approvals from being acted on</p> | |
| 33 | +<p>• Improved agent view: sessions that edit, merge, comment on, or push to an existing PR now link it in claude agents</p> | |
| 34 | +<p>• Improved agent view: rows now show a colored state word and a classifier-written headline instead of raw tool call text, and the peek opens with full status including the exact ask for blocked sessions</p> | |
| 35 | +<p>• /doctor is now a full setup checkup that can diagnose and fix issues; /checkup is its alias</p> | |
| 36 | +<p>• Reserved the "Claude Browser" MCP server name (alongside "Claude Preview") ahead of the Claude Desktop pane rename; user-configured MCP servers can no longer register under either name</p> | |
| 37 | +<p>• Fixed Cowork VM-mode local-agent sessions failing to start with "Not logged in · Please run /login" on CLI 2.1.203+</p></content> | |
| 38 | + </entry> | |
| 39 | + <entry> | |
| 11 | 40 | <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.204</id> |
| 12 | 41 | <title>Claude Code v2.1.204</title> |
| 13 | 42 | <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.204"/> |
| @@ -448,34 +477,4 @@ | ||
| 448 | 477 | <p>• Fixed remote session background tasks appearing stuck as "still running" between turns</p> |
| 449 | 478 | <p>• Improved plugin loading performance in remote sessions</p></content> |
| 450 | 479 | </entry> |
| 451 | - <entry> | |
| 452 | - <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.178</id> | |
| 453 | - <title>Claude Code v2.1.178</title> | |
| 454 | - <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.178"/> | |
| 455 | - <updated>2026-06-15T21:35:48Z</updated> | |
| 456 | - <content type="html"><p>• Agent teams: removed the TeamCreate and TeamDelete tools. With CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 set, every session now has one implicit team — spawn teammates directly with the Agent tool's name parameter, no setup step needed. The team_name parameter on the Agent tool is still accepted but ignored.</p> | |
| 457 | -<p>• Added Tool(param:value) syntax for permission rules to match a tool's input parameters (with * wildcard), e.g. Agent(model:opus) to block Opus subagents</p> | |
| 458 | -<p>• Skills in nested .claude/skills directories now load when working on files there; on a name clash, the nested skill appears as &lt;dir&gt;:&lt;name&gt; so both stay available</p> | |
| 459 | -<p>• Nested .claude/ directories: the agent, workflow, and output-style closest to the working directory now wins when names collide; project-scope workflow saves now target the closest existing .claude/workflows/</p> | |
| 460 | -<p>• Improved auto mode: subagent spawns are now evaluated by the classifier before launch, closing a gap where a subagent could request a blocked action without review</p> | |
| 461 | -<p>• Improved /doctor with consistent flat tree layout across all sections, clearer section status icons, and highlighted command names</p> | |
| 462 | -<p>• Improved the skill listing truncation warning to show how many skill descriptions are affected</p> | |
| 463 | -<p>• Changed the workflow prompt keyword to use a purple shimmer highlight and trigger only on explicit phrases like "run a workflow" or "workflow:", not on any mention of the word</p> | |
| 464 | -<p>• Improved Remote Control error messages: connection failures now show a persistent red "/rc failed" indicator in the footer, and the "not yet enabled" error now explains whether it's a gate, a check failure, stale entitlement, or org policy</p> | |
| 465 | -<p>• /bug now requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title</p> | |
| 466 | -<p>• Fixed a crash (out-of-memory) when the CLI inherits a stale websocket/OAuth file-descriptor environment variable from a parent process</p> | |
| 467 | -<p>• Fixed Claude in Chrome silently failing to connect when the OAuth token belongs to a different account than the Claude Code login</p> | |
| 468 | -<p>• Fixed nested .claude/skills skills with directory-qualified names being blocked by permission prompts in non-interactive runs</p> | |
| 469 | -<p>• Fixed several subagent issues: viewing a subagent's transcript now shows tool results and live progress, messages sent while it finishes its turn are no longer dropped, and backgrounding a running subagent (ctrl+b) no longer restarts it from scratch</p> | |
| 470 | -<p>• Fixed claude agents workers failing with 401 Invalid bearer token when the daemon was started from a shell with a custom API gateway via ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN</p> | |
| 471 | -<p>• Fixed compaction not honoring --fallback-model: compaction now falls back to the configured fallback model chain on overload or model-availability errors</p> | |
| 472 | -<p>• Fixed model requests continuing to fail with auth errors after credentials were refreshed outside the session, due to a stale cached request configuration</p> | |
| 473 | -<p>• Fixed background sessions created with /bg or ←← after a turn finished showing "Working" forever in the agents list</p> | |
| 474 | -<p>• Fixed Linux sandbox failing to start when .claude/skills or .claude/hooks is a symlink</p> | |
| 475 | -<p>• Fixed CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 preventing fresh marketplace installs from cloning</p> | |
| 476 | -<p>• Fixed MCP server-level specs (mcp__server, mcp__server__*, mcp__*) in subagent disallowedTools being silently ignored</p> | |
| 477 | -<p>• Fixed vim mode undo: u now steps through NORMAL/VISUAL-mode commands one at a time instead of merging commands in quick succession into a single undo step</p> | |
| 478 | -<p>• Fixed statusline links with custom URI schemes (e.g. vscode://) not opening when clicked in claude agents</p> | |
| 479 | -<p>• [VSCode] Fixed pressing Esc to dismiss a CJK IME candidate window canceling the running Claude task</p></content> | |
| 480 | - </entry> | |
| 481 | 480 | </feed> |