What are the most popular Claude Code skills?

Ranked by real invocations measured from developers' local agent transcripts, the skills at the top of this page are the ones developers actually run — not the ones with the most GitHub stars or directory listings. The ranking updates as new usage syncs in.

Which MCP servers do developers actually use?

The tool-call table on this page separates MCP server calls (named like server · tool) from built-in agent tools, ranked by real call counts, token burn and error rates measured from local transcripts.

How is skill and tool usage measured?

The whoburnedmore CLI parses the transcripts coding agents keep locally and submits only name + count + token aggregates for skills and tool calls. No prompts, arguments, file names or outputs are collected.

Most-Used Claude Code Skills & MCP Servers — Real Usage Data

SKILLS+MCP

LIVE · 2026-11-13 02:31Z

Skills tracked

100

Skill invocations

936,285

MCP tools

Built-in tools

Tool calls

9,992,105

Developers

358

listed panel

Skills by real usage

100 skills · row fill = vs top skill

#	Skill	Devs	Calls	Tokens
01	superpowers:writing-plans	31	33,884	9.25B
02	code-review	58	55,278	8.64B
03	workflow-authoring	25	54,681	7.94B

MCP server tools

50 tools · server · tool

#	MCP tool	Devs	Calls	Tokens	Err
01	claude-in-chrome · browser_batch	79	33,709	9.61B	5%
02	ccd_turn · update_plan	66	58,296	9.28B

METHODOLOGY — measured, not surveyed: the open-source npx whoburnedmore CLI reads the local usage logs coding agents already keep and submits daily aggregate token totals per tool and model — never prompts, code or file names. Panel = 358 listed developers who opted in publicly, including subscription usage (Claude Code, Cursor, Codex) that API-gateway rankings never see. Costs estimated from public per-token pricing. what we collect · leaderboard · state of AI coding

Built-in agent tools

50 tools

#	Tool	Devs	Calls	Tokens	Err
01	Bash	282	4,765,131	987.16B	3%
02	exec	206	1,216,550	158.09B	0%
03	Read	282	853,436	118.52B	1%
04	Edit	275	453,285	106.52B	2%
05	Write	277	254,808	58.86B	2%
06	exec_command	121	667,453	36.86B	0%
07	WebFetch	250	186,406	17.58B	4%
08	apply_patch	131	114,707	14.46B	0%
09	Agent	239	55,412	13.31B	2%
10	WebSearch	240	117,978	10.46B	1%
11	send_message	102	77,243	10.18B	0%
12	ToolSearch	256	71,305	9.71B	0%
13	write_stdin	104	91,196	9.51B	0%
14	wait	172	62,800	8.53B	0%
15	js	145	54,357	7.64B	0%
16	shell_command	50	138,328	7.36B	0%
17	PowerShell	49	25,870	6.24B	12%
18	StructuredOutput	95	49,015	5.30B	10%
19	SendMessage	145	21,832	5.12B	0%
20	TaskUpdate	126	18,748	4.77B	0%
21	Monitor	187	16,473	4.53B	4%
22	Grep	121	46,128	4.45B	2%
23	SubagentHandback	115	19,739	3.93B	0%
24	AskUserQuestion	257	13,754	3.42B	7%
25	wait_agent	97	53,876	3.11B	0%
26	Artifact	149	10,254	2.84B	5%
27	Skill	243	18,495	2.79B	1%
28	TaskCreate	128	11,074	2.37B	1%
29	TaskStop	211	9,548	2.21B	4%
30	sleep	101	12,301	1.86B	0%
31	shell	10	21,968	1.76B	0%
32	view_file	2	4,692	1.57B	0%
33	SendUserFile	117	4,598	1.54B	2%
34	update_plan	105	13,290	1.48B	0%
35	manage_task	2	2,239	1.36B	0%
36	run_command	3	5,971	1.05B	0%
37	ScheduleWakeup	125	3,232	1.02B	2%
38	Glob	97	24,673	876.6M	1%
39	Workflow	85	2,560	859.6M	6%
40	followup_task	82	8,149	838.0M	0%
41	TodoWrite	33	3,855	790.0M	0%
42	spawn_agent	118	11,149	696.6M	0%
43	write_to_file	2	2,717	629.8M	0%
44	list_agents	88	6,286	602.7M	0%
45	view_image	86	6,561	567.5M	0%
46	replace_file_content	2	1,392	526.8M	0%
47	ArtifactData	23	2,254	411.2M	14%
48	run	17	3,324	377.9M	0%
49	request_user_input_async	119	2,789	370.7M	0%
50	ListAgents	99	1,351	341.6M	0%

SKILLS+MCP

▮Skills by real usage

▮MCP server tools

▮Built-in agent tools

Skills by real usage

MCP server tools

Built-in agent tools