j6-ucp-perfetto-trace-catcher

j6-ucp-perfetto-trace-catcher is a skill for Claude Code, Codex from HorizonRobotics/OE-Skills. It costs 120 tokens per session (2,515 once invoked), scanned A, original, Apache-2.0.

A tool for capturing Perfetto performance traces from a J6 development board running Horizon Robotics' UCP inference software. It transfers setup files to the board and retrieves the resulting .pftrace file.

In plain words
What is it for?
Use it to capture UCP or Perfetto traces, debug scheduling with trace data, and collect trace files from a remote J6 board.
Why use it?
It removes the manual steps of preparing the board, running the trace, and copying the trace back to an X86 computer. The trace helps investigate scheduling and inference performance issues.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to capture UCP or Perfetto traces, debug scheduling with trace data, and collect trace files from a remote J6 board.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-catcher
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add HorizonRobotics/OE-Skills --skill j6-ucp-perfetto-trace-catcher
Clone the repo
git clone --depth 1 https://github.com/HorizonRobotics/OE-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for j6-ucp-perfetto-trace-catcher

README.md
[![agentmods](https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-catcher/github.svg)](https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-catcher)
Your own site
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-catcher"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-catcher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for j6-ucp-perfetto-trace-catcher

Your own site · 80×15
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-catcher"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-catcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.02515
Opus 5 $0.00060 $0.01257
Sonnet 5 $0.00024 $0.00503
Haiku 4.5 $0.00012 $0.00251

Measured 12d ago against content hash 991a1aad09c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

j6-ucp-perfetto-trace-catcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

horizon/skills/ucp/j6-ucp-perfetto-trace-catcher/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UCP Trace Catcher

Capture Perfetto-based UCP traces from a remote J6 development board and bring them back to the X86 host for analysis.

What this skill does

Automates the full lifecycle of UCP Perfetto trace capture:

  1. Transfer config files to the dev board
  2. Set up the trace environment and run the application
  3. Pull the captured trace back to the host
  4. Tell the user what to do next

Only Perfetto trace is in scope — ignore DSP trace and Chrome trace.

Never modify original files in this skill's directory. Copy config files to a temp location under the local current workspace (pwd), edit the copy there, then transfer.

Before starting

You need the following information from the user. Ask for anything not provided:

Parameter Description Example
board_ip IP address or hostname of the dev board 192.168.1.100
board_user SSH username for the board (default: root if not specified, do not use local username) root
work_dir Directory on the board where the UCP app runs /userdata/ucp_test
mode in_process or system system
enable_bpu Whether to capture BPU trace (system mode only, default: false) false
output_name Desired trace filename (default: ucp.pftrace) my_trace.pftrace
app_command The UCP application command to run ./hrt_model_exec perf --model_file model.hbm --frame_count 1000 --thread_num 8

If mode is not specified, ask the user:

  • in_process: captures only UCP process-internal trace (track_event). Does NOT support thread scheduling states, ftrace, memory stats, process stats, or BPU trace. No daemon needed. Good for UCP scheduling logic analysis.
  • system: captures UCP trace + thread scheduling states (ftrace), memory stats, and process stats by default (uses ucp_system.cfg). When BPU trace is enabled, the same ucp_system.cfg is used but BPU trace is additionally turned on via sysfs commands; BPU trace data will appear alongside ftrace data. Needs tracebox daemons. Use system mode when you need system-level visibility beyond UCP internals.

Read the full file on GitHub · 195 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 195 lines · 120 tokens per session scan A 991a1aad09c8

Subscribe to this mod's changes

j6-ucp-perfetto-trace-catcher is a skill published in the GitHub repository HorizonRobotics/OE-Skills (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 120 tokens to every session and 2,515 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

hsb-flash

Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…

NVIDIA/skills · 94 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens