A cockpit for Claude Code: plan bars and subagent strips, context, usage limits with reset countdowns and burn rates, spend, the model route and a pet. Six bar styles, three collapsed looks. CLI and Desktop.
Agent Profiler
See where a slow Claude Code session spends time
A live pane and status entry that split agent time into model wait, tools, subagents and engine overhead, with /profile reports and OTLP traces for Jaeger or Grafana Tempo.
What this mod can do
- Reviewed at commit 93fa0f7
- Writes files
- Connects to the internet
- Reads environment variables
- Sees each tool call before it runs and can block or change it
- Also uses telemetry.log{to=collector}, which this page doesn't describe yet
5 more things it can do
- Adds the /profile-export command
- Adds the /profile-pane command
- Adds the /profile command
- Runs on a timer
- Runs on Claude Code hooks, such as session start
Good to know (3)
- Nothing leaves your machine until you set otlpEndpoint; left empty, traces are only written as files
- Turn prompts, Bash commands and search patterns are exported only with exportCommandText on
- Time inside the model server can't be split: time to first token lumps network, queueing and prefill
Preview
Terminal
⎿ agent-profiler: Agent Profiler pane opened (shown in the terminal and the desktop app).
╭────────────────────────────────────────────────────────────────────────────────────────────────✕─╮
│ 255ms agent time · 1 turn(s) │
│ model ███████░░░░░░░░░░░░░ 33% │
│ tools ░░░░░░░░░░░░░░░░░░░░ 0% │
│ subagents ░░░░░░░░░░░░░░░░░░░░ 0% │
│ engine/other █████████████░░░░░░░ 67% │
│ │
│ Running │
│ idle │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
⚠ agent-profiler: ⏱ model 33% · tools 0%Claude Desktop
What it does
In the author's words
Execution profiler for Claude Code: model wait vs tools vs subagents, live, with OTLP export
- What you see
- A live pane, a status entry, and a toast if export fails
- Works in
- Terminal and Claude Desktop
- Slash commands
- /profile-export, /profile-pane, /profile
- Uses your tokens
- No
- Changes files
- .otlp.json trace files under ~/.claude/agent-profiler
- Network access
- Your own OTLP collector, only if you set otlpEndpoint
- Reviewed commit
- 93fa0f7
- Preview recorded with
- Claude Code 2.1.309
How it works
- Times every turn, model request, tool call and subagent from the start of the session
- Reads tool durations from Claude Code and the token usage the API reports
- Updates a status entry like model 61% - tools 28% at most twice a second
- Writes OTLP trace files after each turn; /profile-pane opens the live pane
Common questions
Why is my Claude Code session slow?
This mod splits agent time into model wait, tool execution, subagents and engine overhead, so you can see which part is large. /profile prints a report for the whole session and /profile turn for the last turn, with tool and model stats, repeated file reads and findings.
How do I send Claude Code traces to Jaeger or Grafana Tempo?
Set otlpEndpoint to your collector's OTLP/HTTP base URL, such as http://localhost:4318, and the mod POSTs each trace batch to /v1/traces. Without it, the trace files in ~/.claude/agent-profiler can be sent by hand. Span names follow the GenAI conventions, like chat <model> and execute_tool <tool>.
Does it measure the model's inference time?
No. It reports what the client can observe. Time to first token mixes network, queueing and prefill, and stream times are waits seen at the client, not time the model spent computing.
Does it work in VS Code or with claude -p?
It still records, exports and answers /profile there, but the pane and status entry only draw in the terminal and the Desktop Code tab.
Badge for your README
Own this listing? Add it to your README. The badge shows the install count as it grows.
[](https://staging.statuslin.es/mods/agent-profiler?utm_source=readme-badge)
Or show the preview card:
[](https://staging.statuslin.es/mods/agent-profiler?utm_source=readme-badge)
More like this
Browse the reviewed mods on statuslin.es in a pane, with their install counts and what each can reach, and put one's install prompt in your prompt box. /gallery opens it. It runs nothing: you read the prompt and send it.
[-]
▄▄▄▀▀▀▀▀▄▄▄
▀ ▀ ▀▀
▀ ▀▄
▀▀▀▀ ▀▀▀▀
▀▀▀▀▀▀▀▀▀▀▀
▄▀▀▀ ▀▀▀ ▀▀▄▄ Lv 5
▀▀ ▀▀▀ ▀▀▀▀▀▀ ●●●●○
▀▀ ▀▀ ♥♥♥♥♡A pixel Pokémon that lives at the right edge of the band above the prompt
✧ ███████████▋ 73% 🗝 Ultima Weapon ✦ app ∙ main
♥ ████████████████████████ 100% 「SAVE POINT」 ✶ Limit Form ◉ 41
Claude Code plan-usage HP bar that reads the Claude auth token to show remaining usage.
Opus 4.8 | app main | ctx 22% | ▶ Fix lease reclaim
Your in-progress Tasqr task, what the queue would hand you next with its pending count, and how much is blocked — alongside model, directory, git branch and context usage. Four styles, from a single line to a boxed panel or two-line meters.
Opus · F:15% ██▍ ▏ A:7% █▏ ▏ ⟳ 3dPer-model and all-model weekly quota meters, showing whether usage is ahead of an even pace and when the allowance resets.
✳ Usage 5h 26% · week 7% · fable 15%
Your official Claude quota: the 5-hour session, weekly, and per-model windows with reset times, read from the same endpoint as /usage rather than estimated from token logs.